Data analysis method and system for barring result of hydropower station

Abstract

The invention discloses a data analysis method and system for a barring result of a hydropower station, and relates to the field of computer data analysis, and the method comprises the steps: obtaining the state data of a barring in a preset time and the real-time state detection information of the barring; performing data analysis on the state data of the turning gear in the preset time to obtain a first data set, a second data set and a third data set; solving the first data set and the third data set through a preset first correlation model to obtain a first processing data set; solving the second data set and the third data set through a preset second correlation model to obtain a second processing data set; fusing the first processing data set and the second processing data set; and inputting the real-time state detection information of the jigger into the jigger state recognition model to obtain the adjustment feature information of the jigger. According to the method, data relevance of all parts of the unit is established, relevant data of all the parts of the unit during turning are read in real time, and the purpose of guiding maintenance and adjustment is achieved.

Description

Technical Field

[0001] The invention belongs to the field of computer data analysis, and in particular relates to a data analysis method and system for hydropower station turning results. Background Art

[0002] In a hydropower station, the cranking results reflect the swing of the axis of the main rotating parts such as the turbine runner, the main shaft of the turbine generator, and the generator rotor after operation, as well as the corresponding state of the axis of the unit. The maintenance personnel make maintenance adjustments based on the analysis of the cranking results to ensure that the geometric center, rotation center, and center of gravity of the rotating parts of the unit are on the same axis to ensure safe and stable operation of the unit. In the existing data analysis of the cranking results, no relationship is established between the swing, level, and air gap data of each part of the unit, resulting in the inability to provide effective maintenance guidance based on the numerical changes of multiple parameters, and the overall data analysis is time-consuming and labor-intensive; therefore, it is necessary to design a data analysis method for the cranking results of a hydropower station to solve the above problems. Summary of the invention

[0003] The technical problem to be solved by the present invention is to provide a data analysis method and system for the turning results of a hydropower station. The scheme is used to solve the problems of incomplete data analysis of the turning results in the prior art, inability to establish the relationship between the data, and time-consuming and labor-intensive. It has the characteristics of being able to establish data correlation among various parts of the unit to realize real-time reading of relevant data of various parts of the unit during turning, thereby achieving the purpose of guiding maintenance and adjustment.

[0004] In order to achieve the above technical effects, the technical solution adopted by the present invention is: A data analysis method for hydropower station turning results, comprising: Obtain the state data of the cranking machine within the preset time and the real-time state detection information of the cranking machine; Performing data analysis on the state data of the cranking gear within a preset time to obtain an analysis data set of the cranking gear result, wherein the analysis data set of the cranking gear result includes a first data set, a second data set and a third data set, wherein the first data set includes the roundness information of the rotor end face and the roundness information of the stator end face, the second data set includes the displacement information of the main shaft air supply pipe, the displacement information of the slip ring and the displacement information of the water guide component, and the third data set is the horizontal information of the mirror plate; Solving the first data set and the third data set by using a preset first correlation model to obtain a first processed data set; Solving the second data set and the third data set by using a preset second correlation model to obtain a second processed data set; Solving the first processed data set and the second processed data set through a preset multi-source data fusion model to obtain fused data of the turning result; Inputting the state data of the cranking within a preset time and the fusion data of the cranking result into a preset recurrent neural network for training to obtain a cranking state recognition model; The real-time state detection information of the turning gear is input into the turning gear state recognition model to obtain the adjustment characteristic information of the turning gear, and the adjustment characteristic information of the turning gear is used to inspect and adjust the turning gear.

[0005] Preferably, the first data set and the third data set are solved by a preset first association model to obtain a first processed data set, the rotor end face roundness information includes the rotor upper end face roundness information and the rotor lower end face roundness information, and the stator end face roundness information includes the stator upper end face roundness information and the stator lower end face roundness information, including: Obtain the rotor roundness weight information and stator roundness weight information of the current hydropower station; A matrix is ​​constructed according to the roundness information of the upper end surface of the rotor, the roundness information of the lower end surface of the rotor, the roundness information of the upper end surface of the stator, the roundness information of the lower end surface of the stator and the horizontal information of the mirror plate within a preset time to obtain the first-level multi-parameter matrix information; Solving the first-level multi-parameter matrix information through an inner product model to obtain the first-level multi-parameter inner product matrix information; Solving the first-level multi-parameter inner product matrix information through a characteristic matrix model to obtain first-level eigenvector matrix information and first-level diagonal matrix information; The rotor roundness weight information, the stator roundness weight information, the first-level eigenvector matrix information and the first-level diagonal matrix information are solved by a first association model to obtain a first processed data set.

[0006] Preferably, the rotor roundness weight information, the stator roundness weight information, the first-level eigenvector matrix information and the first-level diagonal matrix information are solved by a first association model to obtain a first processed data set, wherein the first association model is: ; In the formula, represents the first processed data set, Indicates the rotor roundness weight information, Indicates the stator roundness weight information, Indicates the first-level diagonal matrix information is taken The diagonal matrix with the largest eigenvalue, Indicates the first-level eigenvector matrix information The eigenvector matrix when the maximum eigenvalue is Represents the first preset constant coefficient.

[0007] Preferably, solving the second data set and the third data set by using a preset second correlation model to obtain a second processed data set includes: Obtain the displacement weight information of the main shaft air supply pipe, the displacement weight information of the slip ring and the displacement weight information of the water guide component of the current hydropower station; A matrix is ​​constructed according to the displacement information of the main shaft air supply pipe, the displacement information of the slip ring, the displacement information of the water guide component and the horizontal information of the mirror plate within a preset time to obtain the second-level multi-parameter matrix information; Solving the second-level multi-parameter matrix information through an inner product model to obtain second-level multi-parameter inner product matrix information; Solving the second-level multi-parameter inner product matrix information through a characteristic matrix model to obtain second-level eigenvector matrix information and second-level diagonal matrix information; The displacement weight information of the main shaft air supply pipe, the displacement weight information of the slip ring, the displacement weight information of the water guide component, the second-level eigenvector matrix information and the second-level diagonal matrix information are solved by a second association model to obtain a second processed data set.

[0008] Preferably, the displacement weight information of the main shaft air supply pipe, the displacement weight information of the slip ring, the displacement weight information of the water guide component, the second-level eigenvector matrix information and the second-level diagonal matrix information are solved by a second association model to obtain a second processed data set, wherein the second association model is: ; In the formula, represents the second processed data set, Indicates the displacement weight information of the main axis air supply pipe. Indicates the slip ring displacement weight information, Represents the displacement weight information of the water-conducting component. Indicates that the second-level diagonal matrix information is taken The diagonal matrix with the largest eigenvalue, Indicates the second-level eigenvector matrix information The eigenvector matrix when the maximum eigenvalue is Represents the second preset constant coefficient.

[0009] Preferably, in acquiring the displacement weight information of the water guiding component, calculation of the displacement weight information of the water guiding component includes: Obtaining upper guide displacement weight information, lower guide displacement weight information, water guide displacement weight information, thrust head displacement weight information and rotor lower flange displacement information; Calculating the upper guide displacement weight information and the lower guide displacement weight information to obtain a first judgment coefficient; Calculating the water guide displacement weight information, the thrust head displacement weight information, and the rotor lower flange displacement information to obtain a second judgment coefficient; The first judgment coefficient and the second judgment coefficient are solved by using a preset weight model to obtain displacement weight information of the water guide component.

[0010] Preferably, the state data of the cranking within a preset time and the fusion data of the cranking result are input into a preset recurrent neural network for training to obtain a cranking state recognition model, including: Performing normalization calculation on the state data of the cranking gear within a preset time to obtain normalized data of the cranking gear state; Performing normalization calculation on the fused data of the cranking result to obtain normalized data of the cranking result; The normalized data of the cranking state and the normalized data of the cranking result are input into a preset recurrent neural network for training to obtain a cranking state recognition model, wherein the recurrent neural network includes an input layer, multiple hidden layers and an output layer, each neuron in the hidden layer is a recurrent unit, the input layer is fully connected to the first hidden layer, the last hidden layer is fully connected to the output layer, and a memory unit is arranged between the output layer and the input layer.

[0011] Preferably, a data analysis system for hydropower station turning results comprises: An acquisition module is used to acquire the state data of the turning gear within a preset time and the real-time state detection information of the turning gear; a first processing module, for performing data analysis on the state data of the cranking gear within a preset time to obtain an analysis data set of the cranking gear result, wherein the analysis data set of the cranking gear result includes a first data set, a second data set and a third data set, wherein the first data set includes the roundness information of the rotor end face and the roundness information of the stator end face, the second data set includes the displacement information of the main shaft air supply pipe, the displacement information of the slip ring and the displacement information of the water guide assembly, and the third data set is the horizontal information of the mirror plate; A second processing module, used for solving the first data set and the third data set by using a preset first correlation model to obtain a first processed data set; A third processing module, used for solving the second data set and the third data set by using a preset second correlation model to obtain a second processed data set; a fourth processing module, configured to solve the first processing data set and the second processing data set through a preset multi-source data fusion model to obtain fused data of the turning result; A fifth processing module, for inputting the state data of the cranking gear within a preset time and the fusion data of the cranking gear result into a preset recurrent neural network for training to obtain a cranking gear state recognition model; The identification module is used to input the real-time state detection information of the turning gear into the turning gear state identification model to obtain the adjustment characteristic information of the turning gear, and the adjustment characteristic information of the turning gear is used to inspect and adjust the turning gear.

[0012] Preferably, in the second processing module, the rotor end face roundness information includes the rotor upper end face roundness information and the rotor lower end face roundness information, and the stator end face roundness information includes the stator upper end face roundness information and the stator lower end face roundness information, including: A first acquisition unit is used to acquire rotor roundness weight information and stator roundness weight information of the current hydropower station; A first calculation unit is used to construct a matrix according to the roundness information of the upper end surface of the rotor, the roundness information of the lower end surface of the rotor, the roundness information of the upper end surface of the stator, the roundness information of the lower end surface of the stator and the horizontal information of the mirror plate within a preset time to obtain the first-level multi-parameter matrix information; A second calculation unit, used for solving the first-level multi-parameter matrix information through an inner product model to obtain the first-level multi-parameter inner product matrix information; A third calculation unit is used to solve the first-level multi-parameter inner product matrix information through a characteristic matrix model to obtain first-level eigenvector matrix information and first-level diagonal matrix information; The fourth calculation unit is used to solve the rotor roundness weight information, the stator roundness weight information, the first-level eigenvector matrix information and the first-level diagonal matrix information through a first association model to obtain a first processed data set.

[0013] Preferably, the third processing module includes: The second acquisition unit is used to acquire the displacement weight information of the main shaft air supply pipe, the displacement weight information of the slip ring and the displacement weight information of the water guide component of the current hydropower station; A fifth calculation unit is used to construct a matrix according to the displacement information of the main shaft air supply pipe, the displacement information of the slip ring, the displacement information of the water guide component and the horizontal information of the mirror plate within a preset time to obtain the second-level multi-parameter matrix information; a sixth calculation unit, configured to solve the second-level multi-parameter matrix information by using an inner product model to obtain second-level multi-parameter inner product matrix information; A seventh calculation unit, used for solving the second-level multi-parameter inner product matrix information through a characteristic matrix model to obtain second-level eigenvector matrix information and second-level diagonal matrix information; The eighth calculation unit is used to solve the displacement weight information of the main shaft air supply pipe, the displacement weight information of the slip ring, the displacement weight information of the water guide component, the second-level eigenvector matrix information and the second-level diagonal matrix information through a second association model to obtain a second processed data set.

[0014] The beneficial effects of the present invention are as follows: The present invention first analyzes and classifies the data of each part of the unit, then associates the first data set with the third data set, and associates the second data set with the third data set; then the processed data is merged to ensure the redundancy or complementarity of different processed data in space or time, so as to obtain a focused analysis of the priority items of the turning result; finally, the real-time state detection information of the turning is input into the turning state recognition model to obtain the adjustment feature information of the turning, so as to achieve the purpose of guiding the maintenance and adjustment. This method establishes the data correlation of each part of the unit, realizes the real-time reading of the relevant data of each part of the unit during the turning, and uses the analysis algorithm to automatically complete the data analysis and auxiliary decision-making of the axis adjustment, so as to make the entire turning visualized and simplified, so as to achieve the goal of saving the project maintenance cost and shortening the project construction period. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic flow chart of a method for analyzing data of hydropower station turning results described in an embodiment of the present invention; Figure 2 A topological structure diagram of the data analysis system for hydropower station turning results described in an embodiment of the present invention when in use; Figure 3 This is a schematic diagram of the data calculation principle in an embodiment of the present invention; Figure 4 It is a schematic diagram of the structure of a data analysis device for hydropower station turning results described in an embodiment of the present invention; In the figure: a data analysis device 800 for hydropower station turning results, a processor 801 , a memory 802 , a multimedia component 803 , an I / O interface 804 , and a communication component 805 . DETAILED DESCRIPTION

[0016] Embodiment 1: like Figure 1 As shown, this embodiment provides a data analysis method for the turning results of a hydropower station; Figure 1 It is shown in the figure that the method includes steps S1 to S7, specifically: S1: Obtaining the state data of the cranking machine within a preset time and the real-time state detection information of the cranking machine; In step S1, the cranking mode can be 8-point fixed-point cranking or continuous cranking, and the preset time is determined according to the preset training amount of the recurrent neural network; In terms of data acquisition, for displacement information, a contact displacement sensor is used for data collection; for roundness information, a capacitive sensor is used for data collection, which can adapt to units with different gaps through different magnetic backplates; for spindle rotation signals, a position sensor is used for data collection to facilitate the calculation of the turning angle; for horizontal position information, an electronic horizontal imager is used for measurement.

[0017] Furthermore, the capacitive sensor may adopt a PC25 series sensor, which is designed based on the capacitance principle and can measure the distance between its surface and the object being measured. The measurement signal is sent from the sensor end to the PC25 series signal conditioning module through a high-temperature resistant three-layer shielded coaxial cable, and is transmitted to the calculation module after being corrected by a precise digital linearization algorithm.

[0018] S2: performing data analysis on the state data of the cranking gear within a preset time to obtain an analysis data set of the cranking gear result, wherein the analysis data set of the cranking gear result includes a first data set, a second data set and a third data set, wherein the first data set includes the roundness information of the rotor end face and the roundness information of the stator end face, the second data set includes the displacement information of the main shaft air supply pipe, the displacement information of the slip ring and the displacement information of the water guide component, and the third data set is the horizontal information of the mirror plate; The water guide component displacement information includes upper guide displacement information, lower guide displacement information, water guide displacement information, thrust head displacement information and rotor lower flange displacement information.

[0019] When this method performs data parsing and transmission, the gateway is set up with: ①. Data interface: Pulse is set to collect 2 channels, rate 1kHz, input voltage 0-10V; 485 communication collects 6 channels, the highest rate is 9600, photoelectric isolation; ②. Wireless communication: Lora mode.

[0020] S3: solving the first data set and the third data set by using a preset first correlation model to obtain a first processed data set; To clarify the specific processing process of the first processing data set, the rotor end face roundness information includes the rotor upper end face roundness information and the rotor lower end face roundness information, and the stator end face roundness information includes the stator upper end face roundness information and the stator lower end face roundness information. Step S3 includes S31 to S35, specifically: S31: Obtaining the rotor roundness weight information and stator roundness weight information of the current hydropower station; In step S31, the rotor roundness weight information is determined according to the current maintenance standard of the hydropower station. First, the tolerance range of the rotor roundness is obtained; then, the end point values ​​of the tolerance range are averaged to obtain the mean information of the rotor roundness; finally, the mean information of the rotor roundness is ratio-calculated with a preset roundness threshold to obtain the rotor roundness weight information; The stator roundness weight information is determined according to the tolerance range of the rotational fit between the rotor and the stator in the current hydropower station. Specifically, the end point values ​​of the tolerance range of the rotational fit are subtracted, and then the difference value is multiplied by the rotor roundness weight information to obtain the stator roundness weight information.

[0021] S32: constructing a matrix according to the roundness information of the upper end surface of the rotor, the roundness information of the lower end surface of the rotor, the roundness information of the upper end surface of the stator, the roundness information of the lower end surface of the stator and the horizontal information of the mirror plate within a preset time to obtain the first-level multi-parameter matrix information; In step S32, the first-level multi-parameter matrix information is: ; (1) In the above formula (1), Represents the first-level multi-parameter matrix information, Indicates the characteristic data corresponding to the roundness information of the rotor upper end surface, Indicates the characteristic data corresponding to the roundness information of the lower end surface of the rotor, Indicates the characteristic data corresponding to the roundness information of the upper end surface of the stator. Indicates the characteristic data corresponding to the roundness information of the lower end surface of the stator, Indicates the characteristic data corresponding to the horizontal information of the mirror plate.

[0022] S33: solving the first-level multi-parameter matrix information through an inner product model to obtain the first-level multi-parameter inner product matrix information; In step S33, the inner product model is: ; (2) In the above formula (2), represents the first-level multi-parameter inner product matrix information, Represents the first-level multi-parameter matrix information, Represents the transposed matrix information of the first-level multi-parameter matrix.

[0023] S34: Solving the first-level multi-parameter inner product matrix information through a characteristic matrix model to obtain first-level characteristic vector matrix information and first-level diagonal matrix information; In step S34, the characteristic matrix model uses the existing analytical algorithm to decompose the first-level multi-parameter inner product matrix information to obtain the first-level characteristic vector matrix information And the first-level diagonal matrix information , where the first-level diagonal matrix information ,in ; S35: Solve the rotor roundness weight information, the stator roundness weight information, the first-level eigenvector matrix information and the first-level diagonal matrix information through a first association model to obtain a first processed data set.

[0024] In step S35, the first association model is: ; (3) In the above formula (3), represents the first processed data set, Indicates the rotor roundness weight information, Indicates the stator roundness weight information, Indicates that the first-level diagonal matrix information is taken The diagonal matrix with the largest eigenvalue, Indicates the first-level eigenvector matrix information The eigenvector matrix when the maximum eigenvalue is represents the first preset constant coefficient, Related to the current maintenance standards of hydropower stations.

[0025] S4: Solving the second data set and the third data set by using a preset second correlation model to obtain a second processed data set; to clarify the specific processing process of the second processed data set, this step includes steps S41 to S45, specifically: S41: Obtain the displacement weight information of the main shaft air supply pipe, the displacement weight information of the slip ring and the displacement weight information of the water guide component of the current hydropower station; In step S41, the calculation principle of the displacement weight information of the main shaft air supply pipe and the displacement weight information of the slip ring is the same as the calculation principle of the rotor roundness weight information in step S31.

[0026] In step S41, in obtaining the displacement weight information of the water guiding component, the calculation of the displacement weight information of the water guiding component includes steps S411 to S414, specifically: S411: Acquire upper guide displacement weight information, lower guide displacement weight information, water guide displacement weight information, thrust head displacement weight information, and rotor lower flange displacement information; In step S411, the calculation principle of the upper guide displacement weight information, the lower guide displacement weight information, the water guide displacement weight information, the thrust head displacement weight information and the rotor lower flange displacement information is the same as the calculation principle of the rotor roundness weight information in step S31.

[0027] S412: Calculate the upper guide displacement weight information and the lower guide displacement weight information to obtain a first judgment coefficient; In step S412, an average value of the upper guide displacement weight information and the lower guide displacement weight information is calculated to obtain a first judgment coefficient.

[0028] S413: Calculating the water guide displacement weight information, the thrust head displacement weight information, and the rotor lower flange displacement information to obtain a second judgment coefficient; In this step, the average of the above three is calculated to obtain the second judgment coefficient.

[0029] S414: Solving the first judgment coefficient and the second judgment coefficient by using a preset weight model to obtain displacement weight information of the water guiding component.

[0030] ; (4) In the above formula (4), Represents the displacement weight information of the water-conducting component. represents the first judgment coefficient, represents the first judgment coefficient, and Both represent preset adjustment parameters, which are related to the maximum displacement of the water guide component.

[0031] S42: constructing a matrix according to the displacement information of the main shaft air supply pipe, the displacement information of the slip ring, the displacement information of the water guide assembly and the horizontal information of the mirror plate within a preset time to obtain the second-level multi-parameter matrix information; In this step S42, the second-level multi-parameter matrix information is: ; (5) In the above formula (5), Represents the second-level multi-parameter matrix information, Indicates the displacement information of the main shaft air supply pipe. Indicates the slip ring displacement information, Indicates the displacement information of the water guide component. Indicates the characteristic data corresponding to the horizontal information of the mirror plate.

[0032] S43: solving the second-level multi-parameter matrix information by using an inner product model to obtain the second-level multi-parameter inner product matrix information; In step S43, the inner product model is: ; (6) In the above formula (6), represents the second-level multi-parameter inner product matrix information, Represents the second-level multi-parameter matrix information, Represents the transposed matrix information of the second-level multi-parameter matrix.

[0033] S44: solving the second-level multi-parameter inner product matrix information through a characteristic matrix model to obtain second-level eigenvector matrix information and second-level diagonal matrix information; In step S44, the characteristic matrix model uses the existing analytical algorithm to decompose the second-level multi-parameter inner product matrix information to obtain the second-level characteristic vector matrix information and the second-level diagonal matrix information , where the second-level diagonal matrix information ,in ; S45: Solving the displacement weight information of the main shaft air supply pipe, the displacement weight information of the slip ring, the displacement weight information of the water guide component, the second-level eigenvector matrix information and the second-level diagonal matrix information through a second association model to obtain a second processed data set.

[0034] In step S45, the second association model is: ; (7) In the above formula (7), represents the second processed data set, Indicates the displacement weight information of the main axis air supply pipe. Indicates the slip ring displacement weight information, Represents the displacement weight information of the water-conducting component. Indicates that the second-level diagonal matrix information is taken The diagonal matrix with the largest eigenvalue, Indicates the second-level eigenvector matrix information The eigenvector matrix when the maximum eigenvalue is Represents the second preset constant coefficient.

[0035] S5: Solving the first processed data set and the second processed data set through a preset multi-source data fusion model to obtain fused data of the turning result; In step S5, the preset multi-source data fusion model may adopt the existing DS fusion algorithm or entropy theory algorithm.

[0036] S6: inputting the state data of the cranking within a preset time and the fusion data of the cranking result into a preset recurrent neural network for training to obtain a cranking state recognition model; In step S6, steps S61 to S63 are included, specifically: S61: performing normalization calculation on the state data of the cranking gear within a preset time to obtain normalized data of the cranking gear state; S62: performing normalization calculation on the fused data of the turning result to obtain normalized data of the turning result; In step S61 and step S62, the normalization calculation adopts the existing Z-Score model.

[0037] S63: Input the normalized data of the cranking state and the normalized data of the cranking result into a preset recurrent neural network for training to obtain a cranking state recognition model, wherein the recurrent neural network includes an input layer, multiple hidden layers and an output layer, each neuron in the hidden layer is a recurrent unit, the input layer is fully connected to the first hidden layer, the last hidden layer is fully connected to the output layer, and a memory unit is arranged between the output layer and the input layer.

[0038] In step S63, each neuron in the hidden layer is a recurrent unit, wherein when each recurrent unit performs recurrent learning, it includes S631 to S634, specifically: S631: Obtain the input weights of the forward neural network, the input weights of the backward neural network, and the hidden layer function; S632: learning the input weights and hidden layer functions of the feedforward neural network through a preset feedforward learning model to obtain output data of the feedforward recurrent unit; In step S62, the forward learning model adopts the forward propagation model in LSTM.

[0039] S633: learning the input weights and hidden layer functions of the backward neural network through a preset backward learning model to obtain output data of the backward recurrent unit; In step S63, the backward learning model adopts the back propagation model in LSTM.

[0040] S634: Connect the output data of the forward cycle unit and the output data of the backward cycle unit through a preset connection function to obtain the output data of the current cycle unit.

[0041] In step S634, the preset connection function is: ; (8) In the above formula (8), Indicated in The output data of the current cycle unit at time, represents the preset activation function, represents the preset weight matrix corresponding to the output data of the forward recurrent unit and the output data of the backward recurrent unit, represents the output data of the forward cycle unit, Represents the output data of the backward recurrent unit.

[0042] S7: Input the real-time state detection information of the turning gear into the turning gear state recognition model to obtain the adjustment characteristic information of the turning gear, and the adjustment characteristic information of the turning gear is used to inspect and adjust the turning gear.

[0043] Since data association has been performed in the previous data analysis, in this step, the corresponding components can be adjusted according to the adjustment characteristic information of the turning gear. The adjustment characteristic information of the turning gear is a multi-level setting, such as a ten-level gradient setting, specifically: In the first to third levels, the roundness of the rotor end face and the stator end face are the priority adjustment objects, and the displacement of the main shaft air supply pipe, the displacement of the slip ring, the displacement of the water guide component and the horizontal position of the mirror plate are set as the same level adjustment objects; In the fourth to seventh levels, the displacement of the main shaft air supply pipe, the displacement of the slip ring, and the displacement of the water guide assembly are the priority adjustment objects, and the roundness of the rotor end face, the roundness of the stator end face, and the horizontal position of the mirror plate are set as the same level adjustment objects; among them, in the fifth and sixth levels, the adjustment level of the water guide assembly displacement is higher than the adjustment level of the main shaft air supply pipe displacement and the slip ring displacement; In the eighth to tenth levels, the horizontal position of the mirror plate is the priority adjustment object, and the rotor end face roundness, stator end face roundness, main shaft air supply pipe displacement, slip ring displacement, and water guide component displacement are set as the same level adjustment objects.

[0044] Based on the above steps, in this method, the data of each part of the unit are first analyzed and classified, and then the first data set and the third data set are associated, and the second data set and the third data set are associated; then the processed data are fused to ensure the redundancy or complementarity of different processed data in space or time, so as to obtain a focused analysis of the priority items of the turning results; finally, the real-time state detection information of the turning is input into the turning state recognition model to obtain the adjustment feature information of the turning, so as to achieve the purpose of guiding the maintenance adjustment. This method establishes the data correlation of each part of the unit, realizes the real-time reading of the relevant data of each part of the unit during the turning, and uses the analysis algorithm to automatically complete the data analysis and auxiliary decision-making of the axis adjustment, so as to make the entire turning visualized and simplified, so as to achieve the goal of saving the project maintenance cost and shortening the project construction period.

[0045] Embodiment 2: like Figure 2 As shown, this is a topological structure diagram of a data analysis system for the turning results of a hydropower station. Specifically, the following steps are taken: first, the parameters at different component positions are collected, and then the parameters at different component positions are input into the analysis system. The analysis system outputs the adjustment characteristic information of the turning gear, and finally, the corresponding position of the turning gear is inspected and adjusted according to the adjustment characteristic information of the turning gear.

[0046] This embodiment provides a data analysis system for hydropower station turning results, the system comprising: An acquisition module is used to acquire the state data of the turning gear within a preset time and the real-time state detection information of the turning gear; a first processing module, for performing data analysis on the state data of the cranking gear within a preset time to obtain an analysis data set of the cranking gear result, wherein the analysis data set of the cranking gear result includes a first data set, a second data set and a third data set, wherein the first data set includes the roundness information of the rotor end face and the roundness information of the stator end face, the second data set includes the displacement information of the main shaft air supply pipe, the displacement information of the slip ring and the displacement information of the water guide assembly, and the third data set is the horizontal information of the mirror plate; A second processing module, used for solving the first data set and the third data set by using a preset first correlation model to obtain a first processed data set; A third processing module, used for solving the second data set and the third data set by using a preset second correlation model to obtain a second processed data set; a fourth processing module, configured to solve the first processing data set and the second processing data set through a preset multi-source data fusion model to obtain fused data of the turning result; A fifth processing module, for inputting the state data of the cranking gear within a preset time and the fusion data of the cranking gear result into a preset recurrent neural network for training to obtain a cranking gear state recognition model; The identification module is used to input the real-time state detection information of the turning gear into the turning gear state identification model to obtain the adjustment characteristic information of the turning gear, and the adjustment characteristic information of the turning gear is used to inspect and adjust the turning gear.

[0047] In an implementation method disclosed in the present invention, in the second processing module 3, the rotor end face roundness information includes the rotor upper end face roundness information and the rotor lower end face roundness information, and the stator end face roundness information includes the stator upper end face roundness information and the stator lower end face roundness information, including: A first acquisition unit is used to acquire rotor roundness weight information and stator roundness weight information of the current hydropower station; A first calculation unit is used to construct a matrix according to the roundness information of the upper end surface of the rotor, the roundness information of the lower end surface of the rotor, the roundness information of the upper end surface of the stator, the roundness information of the lower end surface of the stator and the horizontal information of the mirror plate within a preset time to obtain the first-level multi-parameter matrix information; A second calculation unit, used for solving the first-level multi-parameter matrix information through an inner product model to obtain the first-level multi-parameter inner product matrix information; A third calculation unit is used to solve the first-level multi-parameter inner product matrix information through a characteristic matrix model to obtain first-level eigenvector matrix information and first-level diagonal matrix information; The fourth calculation unit is used to solve the rotor roundness weight information, the stator roundness weight information, the first-level eigenvector matrix information and the first-level diagonal matrix information through a first association model to obtain a first processed data set.

[0048] In an implementation method disclosed in the present invention, the third processing module 4 includes: The second acquisition unit is used to acquire the displacement weight information of the main shaft air supply pipe, the displacement weight information of the slip ring and the displacement weight information of the water guide component of the current hydropower station; A fifth calculation unit is used to construct a matrix according to the displacement information of the main shaft air supply pipe, the displacement information of the slip ring, the displacement information of the water guide component and the horizontal information of the mirror plate within a preset time to obtain the second-level multi-parameter matrix information; a sixth calculation unit, configured to solve the second-level multi-parameter matrix information by using an inner product model to obtain second-level multi-parameter inner product matrix information; A seventh calculation unit, used for solving the second-level multi-parameter inner product matrix information through a characteristic matrix model to obtain second-level eigenvector matrix information and second-level diagonal matrix information; The eighth calculation unit is used to solve the displacement weight information of the main shaft air supply pipe, the displacement weight information of the slip ring, the displacement weight information of the water guide component, the second-level eigenvector matrix information and the second-level diagonal matrix information through a second association model to obtain a second processed data set.

[0049] In this system, the system networking adopts a combination of wired / wireless to maximize the signal stability and ease of use. The wireless transmission protocol of this system adopts LoRa technology. When using LoRa technology, this system has the following advantages: ①, long distance; The signal strength that LoRa can demodulate is one hundred thousandth of that of Bluetooth and ZigBee. In addition, LoRa's ultra-high sensitivity comes from the modulation itself. It does not rely on narrowband (Sigfox uses ultra-narrowband technology), retransmission (NB-IOT uses retransmission technology), or coding redundancy.

[0050] ②. Strong anti-interference ability; LoRa can achieve long-distance transmission. In addition to its sensitivity advantage, another very important factor is its super anti-interference ability. LoRa has extreme anti-interference technology that can still communicate at 20dB below noise, which is not available in existing traditional communication technologies.

[0051] In addition, LoRa also has very good coping capabilities for stronger sudden random interference. If faced with a burst length less than half of the LoRa symbol length or a strong interference with a duty cycle of <50%, LoRa can still demodulate stably and ensure that its sensitivity deterioration is <3dB.

[0052] ③. Low power consumption; LoRa modulation has the characteristics of not relying on narrowband, retransmission, and coding redundancy. Therefore, LoRa modulation is a very efficient modulation method with very low working current, with a static current of 1pA; receiving current of less than 5mA; and a current of only 45mA when the transmission power is 17dBm.

[0053] like Figure 3 The figure shows a schematic diagram of the data calculation principle of the data analysis system.

[0054] It should be noted that, regarding the system in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0055] Embodiment 3: Corresponding to the above method embodiment, this embodiment also provides a data analysis device for the turning results of a hydropower station. The data analysis device for the turning results of a hydropower station described below and the data analysis method for the turning results of a hydropower station described above can refer to each other.

[0056] Figure 4 FIG. 8 is a block diagram of a data analysis device 800 for hydropower station turning results according to an exemplary embodiment. Figure 4 As shown, the data analysis device 800 for hydropower station cranking results may include: a processor 801 and a memory 802. The data analysis device 800 for hydropower station cranking results may also include one or more of a multimedia component 803, an I / O interface 804, and a communication component 805.

[0057] The processor 801 is used to control the overall operation of the data analysis device 800 for the hydropower station cranking results, so as to complete all or part of the steps in the above-mentioned data analysis method for the hydropower station cranking results. The memory 802 is used to store various types of data to support the operation of the data analysis device 800 for the hydropower station cranking results, and these data may include, for example, instructions for any application or method operated on the data analysis device 800 for the hydropower station cranking results, and application-related data, such as contact data, sent and received messages, pictures, audio, video, etc. The memory 802 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, disk or optical disk. The multimedia component 803 may include a screen and an audio component. The screen may be, for example, a touch screen, and the audio component is used to output and / or input audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signal may be further stored in the memory 802 or sent via the communication component 805. The audio component also includes at least one speaker for outputting audio signals. The I / O interface 804 provides an interface between the processor 801 and other interface modules, and the above-mentioned other interface modules can be keyboards, mice, buttons, etc. These buttons can be virtual buttons or physical buttons. The communication component 805 is used for wired or wireless communication between the data analysis device 800 for the hydropower station turning results and other devices. Wireless communication, such as Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G or 4G, or a combination of one or more of them, so the corresponding communication component 805 can include: Wi-Fi module, Bluetooth module, NFC module.

[0058] In an exemplary embodiment, the data analysis device 800 for the hydropower station cranking results can be implemented by one or more application specific integrated circuits (Application Specific Integrated Circuit, referred to as ASIC), digital signal processors (Digital Signal Processor, referred to as DSP), digital signal processing devices (Digital Signal Processing Device, referred to as DSPD), programmable logic devices (Programmable Logic Device, referred to as PLD), field programmable gate arrays (Field Programmable Gate Array, referred to as FPGA), controllers, microcontrollers, microprocessors or other electronic components to execute the above-mentioned data analysis method for the hydropower station cranking results.

[0059] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, and when the program instructions are executed by a processor, the steps of the above-mentioned data analysis method for hydropower station cranking results are implemented. For example, the computer-readable storage medium may be the above-mentioned memory 802 including program instructions, and the above-mentioned program instructions may be executed by the processor 801 of the data analysis device 800 for hydropower station cranking results to complete the above-mentioned data analysis method for hydropower station cranking results.

[0060] Embodiment 4: Corresponding to the above method embodiment, a readable storage medium is also provided in this embodiment. The readable storage medium described below and the data analysis method for hydropower station turning results described above can refer to each other.

[0061] A readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the data analysis method for hydropower station turning results in the above method embodiment.

[0062] The readable storage medium may specifically be a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or other readable storage medium that can store program codes.

Claims

1. A data analysis method for hydropower station turning results, characterized in that: include: Obtain the state data of the cranking machine within the preset time and the real-time state detection information of the cranking machine; Performing data analysis on the state data of the cranking gear within a preset time to obtain an analysis data set of the cranking gear result, wherein the analysis data set of the cranking gear result includes a first data set, a second data set and a third data set, wherein the first data set includes the roundness information of the rotor end face and the roundness information of the stator end face, the second data set includes the displacement information of the main shaft air supply pipe, the displacement information of the slip ring and the displacement information of the water guide component, and the third data set is the horizontal information of the mirror plate; Solving the first data set and the third data set by using a preset first correlation model to obtain a first processed data set; Solving the second data set and the third data set by using a preset second correlation model to obtain a second processed data set; Solving the first processed data set and the second processed data set through a preset multi-source data fusion model to obtain fused data of the turning result; Inputting the state data of the cranking within a preset time and the fusion data of the cranking result into a preset recurrent neural network for training to obtain a cranking state recognition model; The real-time state detection information of the turning gear is input into the turning gear state recognition model to obtain the adjustment characteristic information of the turning gear, and the adjustment characteristic information of the turning gear is used to inspect and adjust the turning gear.

2. The data analysis method for hydropower station turning results according to claim 1 is characterized in that: The first data set and the third data set are solved by a preset first association model to obtain a first processed data set, wherein the rotor end surface roundness information includes the rotor upper end surface roundness information and the rotor lower end surface roundness information, and the stator end surface roundness information includes the stator upper end surface roundness information and the stator lower end surface roundness information, including: Obtain the rotor roundness weight information and stator roundness weight information of the current hydropower station; A matrix is ​​constructed according to the roundness information of the upper end surface of the rotor, the roundness information of the lower end surface of the rotor, the roundness information of the upper end surface of the stator, the roundness information of the lower end surface of the stator and the horizontal information of the mirror plate within a preset time to obtain the first-level multi-parameter matrix information; Solving the first-level multi-parameter matrix information through an inner product model to obtain the first-level multi-parameter inner product matrix information; Solving the first-level multi-parameter inner product matrix information through a characteristic matrix model to obtain first-level eigenvector matrix information and first-level diagonal matrix information; The rotor roundness weight information, the stator roundness weight information, the first-level eigenvector matrix information and the first-level diagonal matrix information are solved by a first association model to obtain a first processed data set.

3. The data analysis method for hydropower station turning results according to claim 2 is characterized in that: The rotor roundness weight information, the stator roundness weight information, the first-level eigenvector matrix information, and the first-level diagonal matrix information are solved by a first association model to obtain a first processed data set, wherein the first association model is: ； In the formula, represents the first processed data set, Indicates the rotor roundness weight information, Indicates the stator roundness weight information, Indicates that the first-level diagonal matrix information is taken The diagonal matrix with the largest eigenvalue, Indicates the first-level eigenvector matrix information The eigenvector matrix when the eigenvalue is the largest, Represents the first preset constant coefficient.

4. The data analysis method for hydropower station turning results according to claim 1 is characterized in that: Solving the second data set and the third data set by using a preset second correlation model to obtain a second processed data set includes: Obtain the displacement weight information of the main shaft air supply pipe, the displacement weight information of the slip ring and the displacement weight information of the water guide component of the current hydropower station; A matrix is ​​constructed according to the displacement information of the main shaft air supply pipe, the displacement information of the slip ring, the displacement information of the water guide component and the horizontal information of the mirror plate within a preset time to obtain the second-level multi-parameter matrix information; Solving the second-level multi-parameter matrix information through an inner product model to obtain second-level multi-parameter inner product matrix information; Solving the second-level multi-parameter inner product matrix information through a characteristic matrix model to obtain second-level eigenvector matrix information and second-level diagonal matrix information; The displacement weight information of the main shaft air supply pipe, the displacement weight information of the slip ring, the displacement weight information of the water guide component, the second-level eigenvector matrix information and the second-level diagonal matrix information are solved by a second association model to obtain a second processed data set.

5. The data analysis method for hydropower station turning results according to claim 4 is characterized in that: The displacement weight information of the main shaft air supply pipe, the displacement weight information of the slip ring, the displacement weight information of the water guide component, the second-level eigenvector matrix information and the second-level diagonal matrix information are solved by a second association model to obtain a second processed data set, wherein the second association model is: ； In the formula, represents the second processed data set, Indicates the displacement weight information of the main axis air supply pipe. Indicates the slip ring displacement weight information, Represents the displacement weight information of the water-conducting component. Indicates that the second-level diagonal matrix information is taken The diagonal matrix with the largest eigenvalue, Indicates the second-level eigenvector matrix information The eigenvector matrix when the maximum eigenvalue is Represents the second preset constant coefficient.

6. The data analysis method for hydropower station turning results according to claim 4 is characterized in that: In obtaining the displacement weight information of the water guiding component, the calculation of the displacement weight information of the water guiding component includes: Obtaining upper guide displacement weight information, lower guide displacement weight information, water guide displacement weight information, thrust head displacement weight information and rotor lower flange displacement information; Calculating the upper guide displacement weight information and the lower guide displacement weight information to obtain a first judgment coefficient; Calculating the water guide displacement weight information, the thrust head displacement weight information, and the rotor lower flange displacement information to obtain a second judgment coefficient; The first judgment coefficient and the second judgment coefficient are solved by using a preset weight model to obtain displacement weight information of the water guide component.

7. The data analysis method for hydropower station turning results according to claim 1 is characterized in that: The state data of the cranking within a preset time and the fusion data of the cranking result are input into a preset recurrent neural network for training to obtain a cranking state recognition model, including: Performing normalization calculation on the state data of the cranking gear within a preset time to obtain normalized data of the cranking gear state; Performing normalization calculation on the fused data of the cranking result to obtain normalized data of the cranking result; The normalized data of the cranking state and the normalized data of the cranking result are input into a preset recurrent neural network for training to obtain a cranking state recognition model, wherein the recurrent neural network includes an input layer, multiple hidden layers and an output layer, each neuron in the hidden layer is a recurrent unit, the input layer is fully connected to the first hidden layer, the last hidden layer is fully connected to the output layer, and a memory unit is arranged between the output layer and the input layer.

8. A data analysis system for hydropower station turning results, characterized in that: include: An acquisition module is used to acquire the state data of the turning gear within a preset time and the real-time state detection information of the turning gear; a first processing module, for performing data analysis on the state data of the cranking gear within a preset time to obtain an analysis data set of the cranking gear result, wherein the analysis data set of the cranking gear result includes a first data set, a second data set and a third data set, wherein the first data set includes the roundness information of the rotor end face and the roundness information of the stator end face, the second data set includes the displacement information of the main shaft air supply pipe, the displacement information of the slip ring and the displacement information of the water guide assembly, and the third data set is the horizontal information of the mirror plate; A second processing module, used for solving the first data set and the third data set by using a preset first correlation model to obtain a first processed data set; A third processing module, used for solving the second data set and the third data set by using a preset second correlation model to obtain a second processed data set; a fourth processing module, configured to solve the first processing data set and the second processing data set through a preset multi-source data fusion model to obtain fused data of the turning result; A fifth processing module, for inputting the state data of the cranking gear within a preset time and the fusion data of the cranking gear result into a preset recurrent neural network for training to obtain a cranking gear state recognition model; The identification module is used to input the real-time state detection information of the turning gear into the turning gear state identification model to obtain the adjustment characteristic information of the turning gear, and the adjustment characteristic information of the turning gear is used to inspect and adjust the turning gear.

9. The data analysis system for hydropower station turning results according to claim 8 is characterized in that: In the second processing module, the rotor end surface roundness information includes the rotor upper end surface roundness information and the rotor lower end surface roundness information, and the stator end surface roundness information includes the stator upper end surface roundness information and the stator lower end surface roundness information, including: A first acquisition unit is used to acquire rotor roundness weight information and stator roundness weight information of the current hydropower station; A first calculation unit is used to construct a matrix according to the roundness information of the upper end surface of the rotor, the roundness information of the lower end surface of the rotor, the roundness information of the upper end surface of the stator, the roundness information of the lower end surface of the stator and the horizontal information of the mirror plate within a preset time to obtain the first-level multi-parameter matrix information; A second calculation unit, used for solving the first-level multi-parameter matrix information through an inner product model to obtain the first-level multi-parameter inner product matrix information; A third calculation unit is used to solve the first-level multi-parameter inner product matrix information through a characteristic matrix model to obtain first-level eigenvector matrix information and first-level diagonal matrix information; The fourth calculation unit is used to solve the rotor roundness weight information, the stator roundness weight information, the first-level eigenvector matrix information and the first-level diagonal matrix information through a first association model to obtain a first processed data set.

10. The data analysis system for hydropower station turning results according to claim 8, characterized in that: The third processing module includes: The second acquisition unit is used to acquire the displacement weight information of the main shaft air supply pipe, the displacement weight information of the slip ring and the displacement weight information of the water guide component of the current hydropower station; A fifth calculation unit is used to construct a matrix according to the displacement information of the main shaft air supply pipe, the displacement information of the slip ring, the displacement information of the water guide component and the horizontal information of the mirror plate within a preset time to obtain the second-level multi-parameter matrix information; a sixth calculation unit, configured to solve the second-level multi-parameter matrix information by using an inner product model to obtain second-level multi-parameter inner product matrix information; A seventh calculation unit, used for solving the second-level multi-parameter inner product matrix information through a characteristic matrix model to obtain second-level eigenvector matrix information and second-level diagonal matrix information; The eighth calculation unit is used to solve the displacement weight information of the main shaft air supply pipe, the displacement weight information of the slip ring, the displacement weight information of the water guide component, the second-level eigenvector matrix information and the second-level diagonal matrix information through a second association model to obtain a second processed data set.

Images