A capacitive cylinder expansion differential measuring device for steam turbines

Abstract

This invention provides a capacitive cylinder block differential expansion measurement device for steam turbines, comprising: a capacitive cylinder expansion sensor and a conditioning circuit; the capacitive cylinder expansion sensor includes a first capacitor plate and a second capacitor plate, the first capacitor plate being disposed on the side of the rotor-side measuring disk facing the differential expansion support, and the second capacitor plate being disposed on the side of the differential expansion support facing the measuring disk, and spaced apart from the first capacitor plate; the capacitive cylinder expansion sensor is used to detect the relative displacement change between the measuring disk and the differential expansion support, and converts the displacement change into a capacitance signal; the conditioning circuit is used to condition the capacitance signal, converting it into a DC signal proportional to the differential expansion, and sending the DC signal to a host computer; the host computer is used to determine the differential expansion value of the cylinder block based on the received DC signal. This makes the measurement results more accurate and reliable.

Description

Technical Field

[0001] This invention relates to the field of steam turbine testing technology, specifically to a capacitive cylinder block differential expansion measuring device for steam turbines. Background Technology

[0002] As the "stethoscope" ensuring the operation of the unit, the accuracy of the measured values ​​and the reliability of the protective actions of the rotating machinery monitoring system are of great significance to the safe and economical service of the rotating machinery. Sensors, as the sensing front end of the monitoring, can directly reflect the operating status of the unit through the measured values, and some of these values ​​are involved in the protection logic design. Therefore, the accuracy of the measured values ​​detected by the sensors is of great importance to the safe and stable operation of the unit.

[0003] Cylinder expansion is also an important measurement in the monitoring system. When the steam turbine starts heating, runs cooling, or experiences load changes, both the turbine cylinder and rotor expand / contract to a certain extent. Due to differences in their mass and heated surface area, their expansion / contraction patterns differ, resulting in a relative difference (referred to as expansion differential). When this difference reaches a certain value, it can cause friction between the moving and stationary parts. Existing cylinder expansion sensors for steam turbines generally employ the displacement principle, that is, a sensor is fixed on the turbine cylinder to measure the relative displacement between the turbine cylinder and the rotor. The displacement principle transforms the measurement of the distance between the cylinder surface and the rotor surface into the measurement of the distance between a point (displacement sensor) installed on the cylinder and the rotor. Therefore, the installation position of this type of displacement sensor has extremely high requirements; the point where the displacement is measured must be sufficiently flat and characterize the overall operating state of the cylinder. Summary of the Invention

[0004] The present invention aims to at least solve one of the technical problems existing in the prior art, and provides a capacitive cylinder block differential expansion measuring device for steam turbines.

[0005] This invention provides a capacitive cylinder expansion differential measuring device for steam turbines, comprising: a capacitive cylinder expansion sensor and a conditioning circuit; the capacitive cylinder expansion sensor includes a first capacitor plate and a second capacitor plate, the first capacitor plate being disposed on the side of the rotor-side measuring disk facing the expansion differential support, and the second capacitor plate being disposed on the side of the expansion differential support facing the measuring disk, and being disposed at a distance from the first capacitor plate.

[0006] The capacitive cylinder expansion sensor is used to detect the relative displacement change between the measuring plate and the differential expansion bracket, and convert the displacement change into a capacitance signal;

[0007] The conditioning circuit is used to condition the capacitor signal, convert it into a DC signal proportional to the expansion difference, and send the DC signal to the host computer.

[0008] The host computer is used to determine the expansion difference value of the cylinder based on the received DC signal.

[0009] In some possible embodiments, the capacitive cylinder expansion sensor further includes a first polyvinyl chloride sheet and a second polyvinyl chloride sheet;

[0010] The first polyvinyl chloride sheet is fixed to the side of the measuring disc facing the differential expansion bracket, and the first capacitor plate is bonded to the side of the first polyvinyl chloride sheet facing the differential expansion bracket;

[0011] The second polyvinyl chloride sheet is fixed to the side of the expansion bracket facing the measuring plate, and the second capacitor plate is bonded to the side of the second polyvinyl chloride sheet facing the measuring plate.

[0012] In some possible embodiments, the orthographic projection of the first polyvinyl chloride sheet onto the first capacitor plate falls on the outside of the first capacitor plate;

[0013] The orthographic projection of the second polyvinyl chloride sheet onto the second capacitor plate falls on the outer side of the second capacitor plate.

[0014] In some possible embodiments, the conditioning circuit includes: an inverting proportional circuit, a high-pass filter circuit, a rectifier circuit, a low-pass filter circuit, and an AD conversion circuit;

[0015] The inverting proportional circuit is used to convert the capacitor signal into an AC voltage signal.

[0016] The high-pass filter circuit is used to extract the AC component from the AC voltage signal;

[0017] The rectifier circuit is used to convert the AC voltage signal into a positive pulsating DC signal.

[0018] The low-pass filter circuit is used to remove the ripple signal in the pulsating DC signal, smooth the output, and convert it into a DC voltage signal.

[0019] The AD conversion circuit is used to convert the DC voltage signal into a digital signal and send it to the host computer.

[0020] In some possible embodiments, the high-pass filter circuit is a high-pass filter, the rectifier circuit is a bridge rectifier circuit, and the low-pass filter circuit is a low-pass filter.

[0021] In some possible embodiments, the host computer is further used for:

[0022] After outlier removal, the received DC signal is fed into a pre-trained deep learning model for prediction. The deep learning model uses an LSTM neural network architecture and is trained based on historical expansion data to predict the normal expansion range under the current operating conditions.

[0023] When the deviation between the predicted value and the actual measured value exceeds the set threshold, it is judged as an abnormal state, and a risk warning signal is issued according to the degree of deviation.

[0024] In some possible embodiments, the host computer is further used for:

[0025] The DC signal is subjected to outlier detection and removal using the Z-Score normalization method, and missing data is interpolated.

[0026] The time-frequency characteristics and probability distribution characteristics of the signal are extracted using time-frequency analysis methods and variational autoencoders (VAEs).

[0027] A timing prediction model is built based on an LSTM network, and the future output voltage value is predicted by a sliding window method.

[0028] Establish a spatial vector representation model for four states: normal, slight abnormality, moderate abnormality, and severe abnormality;

[0029] Real-time calculation of the spatial distance between current data characteristics and four states, and determination of device status based on the nearest neighbor principle;

[0030] When an abnormal state is detected, an early warning signal of the corresponding level is triggered based on the level of abnormality.

[0031] In some possible embodiments, the conditioning circuit is arranged inside a shielded box made of metal and rigidly connected to the inside of the cylinder.

[0032] In some possible embodiments, the conditioning circuit is electrically connected to the first capacitor plate and the second capacitor plate via a shielded wire.

[0033] In some possible embodiments, the length of the first capacitor plate and the second capacitor plate ranges from 80mm to 100mm, and the width ranges from 30mm to 50mm.

[0034] The turbine capacitive cylinder expansion differential measurement device of this invention features a capacitive cylinder expansion sensor with a simple structure, small size, and low cost. By applying an excitation signal to the capacitive cylinder expansion sensor, the capacitance value between the capacitor plates is measured, and the capacitance signal is processed in a simple and accurate manner. This invention achieves cylinder expansion value measurement by outputting a DC signal through a conditioning circuit, reducing costs while converting the distance value between a point and a surface into the distance value between surfaces. This reduces the flatness requirements of the plane and makes the measurement results more accurate and reliable. Attached Figure Description

[0035] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0036] Figure 1 This is a schematic diagram of the structure of the capacitive cylinder block differential expansion measuring device for steam turbines according to an embodiment of the present invention;

[0037] Figure 2 for Figure 1 The image shows a bottom view of the installation location of the capacitive cylinder expansion sensor in the capacitive cylinder block differential expansion measuring device for steam turbines.

[0038] Figure 3 This is a schematic diagram of the expansion difference measurement process according to an embodiment of the present invention;

[0039] Figure 4 This is a schematic diagram of the conditioning circuit according to an embodiment of the present invention. Detailed Implementation

[0040] To enable those skilled in the art to better understand the technical solutions of the present invention, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the described embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0041] Unless otherwise specifically stated, the technical or scientific terms used in the embodiments of this invention should be understood in their ordinary sense by those skilled in the art to which this invention pertains. The terms "comprising" or "including," as used in the embodiments of this invention, do not limit the shapes, numbers, steps, actions, operations, components, elements, and / or groups thereof mentioned, nor do they exclude the appearance or addition of one or more other different shapes, numbers, steps, actions, operations, components, elements, and / or groups thereof, or the addition of these. Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number and order of the indicated technical features. Thus, a feature defined with "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of the embodiments of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0042] Unless otherwise specifically stated, the relative arrangement, numerical expressions, and values ​​of the components and steps described in these embodiments do not limit the scope of the invention. It should also be understood that, for ease of description, the dimensions of the various parts shown in the drawings are not drawn to actual scale, and techniques, methods, and apparatus known to those skilled in the art may not be discussed in detail; however, where appropriate, the illustrated techniques, methods, and apparatus should be considered part of the specification. In all the examples shown and discussed herein, any other specific example may have different values. It should be noted that similar symbols and letters in the following figures denote similar items; therefore, once an item is defined in one figure, it need not be further discussed in subsequent figures.

[0043] In the description of the embodiments of the present invention, the terms "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., refer to specific features, structures, materials, or characteristics described in connection with that embodiment or example, which are included in at least one embodiment or example of the present invention. In the embodiments of the present invention, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described may be combined in a suitable manner in any one or more embodiments or examples. Furthermore, without contradiction, those skilled in the art can combine and integrate the different embodiments or examples described in the embodiments of the present invention, as well as the features of different embodiments or examples.

[0044] Hereinafter, exemplary embodiments according to the present invention will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are merely some embodiments of the present invention, and not all embodiments of the present invention. It should be understood that the present invention is not limited to the exemplary embodiments described herein.

[0045] Figure 1 This is a schematic diagram of the structure of the capacitive cylinder block differential expansion measuring device for steam turbines according to an embodiment of the present invention. Figure 2 for Figure 1 The image shows a bottom view of the mounting location of the capacitive cylinder expansion sensor in a capacitive cylinder block differential expansion measuring device for steam turbines. (See image.) Figure 1 and Figure 2 As shown, this embodiment of the invention relates to a capacitive cylinder expansion differential measuring device for steam turbines, comprising: a capacitive cylinder expansion sensor and a conditioning circuit. The capacitive cylinder expansion sensor includes a first capacitor plate 1 and a second capacitor plate 2. The first capacitor plate 1 is disposed on the side of the rotor-side measuring disk 100 facing the expansion differential support 200, and the second capacitor plate 2 is disposed on the side of the expansion differential support 200 facing the measuring disk 100, and is spaced apart from the first capacitor plate 1.

[0046] Specifically, such as Figure 1 As shown, the capacitive cylinder expansion sensor is used to detect the relative displacement change between the measuring disc 100 and the differential expansion bracket 200, and converts the displacement change into a capacitance signal; the conditioning circuit is used to condition the capacitance signal, convert it into a DC signal proportional to the differential expansion, and send the DC signal to the host computer 300; the host computer 300 is used to determine the differential expansion value of the cylinder body based on the received DC signal.

[0047] The turbine capacitive cylinder expansion differential measurement device of this invention features a capacitive cylinder expansion sensor with a simple structure, small size, and low cost. By applying an excitation signal to the capacitive cylinder expansion sensor, the capacitance value between the capacitor plates is measured, and the capacitance signal is processed in a simple and accurate manner. This invention achieves cylinder expansion value measurement by outputting a DC signal through a conditioning circuit, reducing costs while converting the distance value between a point and a surface into the distance value between surfaces. This reduces the flatness requirements of the plane and makes the measurement results more accurate and reliable.

[0048] For example, such as Figure 1 As shown, the capacitive cylinder expansion sensor further includes a first polyvinyl chloride sheet 3 and a second polyvinyl chloride sheet 4; the first polyvinyl chloride sheet 3 is fixed to the side of the measuring disk 100 facing the expansion difference support 200, and the first capacitor plate 1 is bonded to the side of the first polyvinyl chloride sheet 3 facing the expansion difference support 200; the second polyvinyl chloride sheet 4 is fixed to the side of the expansion difference support 200 facing the measuring disk 100, and the second capacitor plate 2 is bonded to the side of the second polyvinyl chloride sheet 4 facing the measuring disk 100.

[0049] In some embodiments, such as Figure 1As shown, the orthographic projection of the first polyvinyl chloride sheet 3 onto the first capacitor plate 1 falls on the outside of the first capacitor plate 1; the orthographic projection of the second polyvinyl chloride sheet 4 onto the second capacitor plate 2 falls on the outside of the second capacitor plate 2. That is, as... Figure 1 As shown, the PVC sheet is slightly larger than the capacitor plates and is rigidly connected to the measuring disc / cylinder support around its perimeter. Most of the PVC sheet bonded to the capacitor plates is used for rigid connection to the cylinder body. This ensures insulation between the electrodes and the measuring disc / cylinder body. In some embodiments, both the first capacitor plate 1 and the second capacitor plate 2 are elongated strips, and each capacitor plate is bonded to the corresponding PVC sheet using J-2012 type epoxy resin adhesive.

[0050] In some embodiments, the capacitor plates mentioned above may be made of conductive metals, such as copper or stainless steel. The size can be determined based on the size of the measuring pan, spatial distance, measurement accuracy requirements, etc. Unless otherwise specified, the length can be between 80 and 100 mm, and the width between 30 and 50 mm.

[0051] When assembling the aforementioned capacitive cylinder block differential expansion measuring device for steam turbines, the first capacitor plate 1 and the second capacitor plate 2 are first fixed to the center positions of the first polyvinyl chloride sheet 3 and the second polyvinyl chloride sheet 4 using J-2012 type epoxy resin adhesive. The first polyvinyl chloride sheet 3 and the second polyvinyl chloride sheet 4 are rigidly connected to the measuring disk 100 and the differential expansion bracket 200 respectively using screws 5 around their perimeters. This ensures that the capacitor plates are insulated from the measuring disk 100 and the differential expansion bracket 200. In some embodiments, the first capacitor plate 1 and the second capacitor plate 2 are connected to a signal conditioning circuit via a shielded wire 6 to reduce interference from external stray signals on the electrode output signal.

[0052] For example, such as Figure 1 and Figure 3 As shown, the conditioning circuit includes: an inverting proportional circuit A, a high-pass filter circuit B, a rectifier circuit C, a low-pass filter circuit D, and an AD conversion circuit E. The inverting proportional circuit A converts the capacitor signal into an AC voltage signal; the high-pass filter circuit B extracts the AC component from the AC voltage signal; the rectifier circuit C converts the AC voltage signal into a positive pulsating DC signal; the low-pass filter circuit D removes the ripple signal from the pulsating DC signal, smooths the output, and converts it into a DC voltage signal; the AD conversion circuit E converts the DC voltage signal into a digital signal and sends it to the host computer 300. In some embodiments, the high-pass filter circuit is a high-pass filter, the rectifier circuit is a bridge rectifier circuit, and the low-pass filter circuit is a low-pass filter.

[0053] Specifically, in this embodiment, due to the relative displacement of the cylinder and rotor during thermal expansion / contraction, the spacing between the capacitor plates mounted on their surfaces changes. At this time, the output capacitance value is inversely proportional to the expansion difference. An inverting proportional circuit A is used to process the capacitance signal; the output voltage is then inversely proportional to the capacitance value, and directly proportional to the expansion difference. This conditioning circuit processes the capacitance signal. When relative displacement occurs between the cylinder and rotor, the conditioning circuit outputs a voltage, which is then rectified and filtered. The processed DC voltage is directly proportional to the relative displacement, thus achieving the purpose of measuring the cylinder expansion difference. Due to the use of a novel capacitive sensor structure, this sensor can be used to measure the spacing between non-flat surfaces, improving sensitivity, reducing interference, and making the measurement results more accurate. Simultaneously, this sensor has low cost, simple structure, and strong resistance to harsh environments, making it widely applicable in various industrial processes. Furthermore, based on model predictions of future data, abnormal states in cylinder expansion values ​​can be detected, enabling risk warnings.

[0054] Please refer to the above. Figure 4 The first capacitor plate 1 and the second capacitor plate 2 used for detection form a capacitive sensor Cx, which serves as the feedback capacitor for the inverting proportional circuit. The output of the inverting proportional circuit can then be expressed as follows:

[0055]

[0056] In the formula:

[0057] U o — Output voltage of the inverting proportional circuit; f — Frequency of the input excitation voltage; U s —Input excitation voltage; C x —The capacitance being measured; C o —Reference capacitor.

[0058] From the formula for parallel plate capacitance, we know that:

[0059]

[0060] In the formula:

[0061] Cx — the capacitance being measured; — Dielectric constant of the medium; S — Plate area of ​​the parallel plates; d — Spacing between the parallel plates.

[0062] That is, the capacitance is inversely proportional to the distance between the parallel plates of the capacitor. This can be summarized as follows:

[0063]

[0064] In the formula:

[0065] U o—Output voltage of the inverting proportional circuit; C o —Reference capacitance; —Dielectric constant of the dielectric; S—Area of ​​the parallel plates; U s —Input excitation voltage; d —Plate spacing between parallel plates.

[0066] As can be seen from the above formula, the magnitude of the output voltage is positively correlated with the spacing between the parallel plates of the capacitor.

[0067] The output voltage, after being high-pass filtered to retain the AC component, enters the AC-DC conversion filter module. In this module, when AC voltage is input to the bridge rectifier circuit, the diodes, based on their unidirectional conduction principle, allow current to flow unidirectionally through the load. Thus, both the positive and negative half-cycles of the AC voltage are converted into DC voltage in the same direction. This voltage then passes through a filter circuit to remove the AC component, retaining the DC component, reducing the ripple factor, and obtaining a stable voltage before being converted by an analog-to-digital converter (AD) and uploaded.

[0068] For example, such as Figure 1 and Figure 3 As shown, the host computer 300 is further configured to: remove outliers from the received DC signal and then send it to a pre-trained deep learning model for prediction; wherein the deep learning model adopts an LSTM neural network architecture, is trained based on historical expansion difference data, and is used to predict the normal expansion difference range under the current operating conditions; when the deviation between the predicted value and the actual measured value exceeds a set threshold, it is determined to be an abnormal state, and a risk warning signal is issued according to the degree of deviation.

[0069] Specifically, such as Figure 1 and Figure 3 As shown, the host computer 300 is further configured to: perform outlier detection and removal on the DC signal using the Z-Score normalization method, and perform interpolation processing on missing data; extract the time-frequency features and probability distribution features of the signal using time-frequency analysis methods and variational autoencoder (VAE); construct a time-series prediction model based on an LSTM network, and predict future output voltage values ​​using a sliding window method; establish a spatial vector representation model for four types of states: normal, slightly abnormal, moderately abnormal, and severely abnormal; calculate the spatial distance between the current data features and the four types of states in real time, and determine the device state based on the nearest neighbor principle; and trigger a warning signal of the corresponding level according to the abnormality level when an abnormal state is detected.

[0070] Specifically, the host computer 300 first uses the Z-Score method to remove outliers that clearly exceed the statistical threshold, thereby improving data quality; it then collects historical values ​​from the past 3 to 6 months as samples, uses machine learning to establish a nonlinear mapping to extract features, and further uses a deep learning model based on time series data to predict data for a future period.

[0071] The specific historical data collected includes output voltage values ​​under stable / normal conditions and output voltage values ​​under marked abnormal conditions (minor, moderate, and severe faults). Output voltage values ​​under stable / normal conditions are used for data prediction during model training, while data values ​​under normal and / or abnormal conditions are used for data early warning during model training. A variational autoencoder (VAE) is employed, which combines a probabilistic model and a neural network to automatically extract the distribution characteristics of the data by maximizing the likelihood function. This extracts features from the original time series that reflect its essential patterns, which can be used for subsequent prediction and anomaly detection. Features include time-domain features, frequency-domain features, and high-level features automatically extracted using an LSTM deep learning model. Data prediction can be performed directly using the trained deep learning model. Simultaneously, the output voltage change trends under abnormal conditions are trained and summarized, then converted into spatial vectors for four-class classification: normal, minor, moderate, and severe abnormal conditions. After obtaining the actual input voltage time series, the features of this time series are extracted, and its spatial distance to four different conditions is determined. The closest distance represents the actual equipment state, allowing for prediction of three anomaly levels: minor, moderate, and severe, and issuing risk warnings accordingly. This involves processing the signal via a host computer to directly calculate, store, transmit, and issue risk warnings for cylinder expansion values. The specific prediction steps are as follows:

[0072] (1) Data processing

[0073] Remove outliers and use interpolation to fill in the missing values.

[0074] (2) Data standardization

[0075] Standardize the data (e.g., Z-Score standardization) to make the data distribution fall within a reasonable range (e.g., [0,1]).

[0076] (3) Construct features and create sliding windows

[0077] The original data and corresponding time are used as features. The window size is n (which can be determined based on the actual number of points collected per minute), and the prediction is made for one future time point. An LSTM (Long Short-Term Memory) model is used for the prediction of time series data.

[0078] (4) Actual model prediction

[0079] After training, by extracting features under normal conditions and training the model, the voltage value at a future time point can be output by inputting the time series data of historical cylinder expansion voltage.

[0080] (5) Real-time status early warning

[0081] Based on the synchronous input of data corresponding to four states—normal, minor, moderate, and severe—into the model, the output voltage change trend under abnormal operating conditions is trained and summarized, and converted into a spatial vector for four-class classification: normal, minor, moderate, and severe abnormal conditions. After inputting the actual voltage time series, the features of the time series are extracted, and its spatial distance from the four states is determined. The closest distance represents the actual equipment state, thereby predicting the three abnormal levels: minor, moderate, and severe.

[0082] In some embodiments, such as Figure 1 and Figure 3 As shown, the conditioning circuit is arranged inside the shielded box 7, which is made of metal and is rigidly connected to the inside of the cylinder. The conditioning circuit is electrically connected to the first capacitor plate 1 and the second capacitor plate 2 via a shielded wire 6.

[0083] Specifically, the PVC sheet is elongated and strip-shaped, typically 0.5mm thick. Its length and width depend on the available installation space for the measuring disc and cylinder, generally 80-100mm in length and 40-60mm in width. The shielding box 7 has a cuboid structure with dimensions of 100mm in length, 100mm in width, and 50mm in height. It is made of metal, grounded, and fixed to the cylinder to form electrostatic shielding. A small circular hole, approximately 5mm in diameter, is located on the side of the shielding box for the shielding wire to pass through. The conditioning circuit is connected to the capacitive cylinder expansion sensor and the host computer 300 via shielded wire 6 passing through the shielding box 7. The circuit board uses surface-mount devices to save space, and its conditioning circuit is located inside the shielding box 7, avoiding interference from stray signals.

[0084] It is understood that the above embodiments are merely exemplary implementations used to illustrate the principles of the present invention, and the present invention is not limited thereto. For those skilled in the art, various modifications and improvements can be made without departing from the spirit and essence of the present invention, and these modifications and improvements are also considered to be within the scope of protection of the present invention.

Claims

1. A capacitive cylinder block differential expansion measuring device for steam turbines, characterized in that, include: A capacitive cylinder expansion sensor and a conditioning circuit; the capacitive cylinder expansion sensor includes a first capacitor plate and a second capacitor plate, the first capacitor plate is disposed on the side of the rotor-side measuring disk facing the expansion difference support, and the second capacitor plate is disposed on the side of the expansion difference support facing the measuring disk, and is disposed at a distance from the first capacitor plate. The capacitive cylinder expansion sensor is used to detect the relative displacement change between the measuring plate and the differential expansion bracket, and convert the displacement change into a capacitance signal; The conditioning circuit is used to condition the capacitor signal, convert it into a DC signal proportional to the expansion difference, and send the DC signal to the host computer. The host computer is used to determine the expansion difference value of the cylinder based on the received DC signal; The capacitive cylinder expansion sensor also includes a first polyvinyl chloride sheet and a second polyvinyl chloride sheet; The first polyvinyl chloride sheet is fixed to the side of the measuring disc facing the differential expansion bracket, and the first capacitor plate is bonded to the side of the first polyvinyl chloride sheet facing the differential expansion bracket; The second polyvinyl chloride sheet is fixed to the side of the expansion bracket facing the measuring plate, and the second capacitor plate is bonded to the side of the second polyvinyl chloride sheet facing the measuring plate; The orthographic projection of the first polyvinyl chloride sheet onto the first capacitor plate falls on the outside of the first capacitor plate, and the orthographic projection of the second polyvinyl chloride sheet onto the second capacitor plate falls on the outside of the second capacitor plate.

2. The capacitive cylinder block differential expansion measuring device for steam turbines according to claim 1, characterized in that, The conditioning circuit includes: an inverting proportional circuit, a high-pass filter circuit, a rectifier circuit, a low-pass filter circuit, and an AD conversion circuit; The inverting proportional circuit is used to convert the capacitor signal into an AC voltage signal. The high-pass filter circuit is used to extract the AC component from the AC voltage signal; The rectifier circuit is used to convert the AC voltage signal into a positive pulsating DC signal. The low-pass filter circuit is used to remove the ripple signal in the pulsating DC signal, smooth the output, and convert it into a DC voltage signal. The AD conversion circuit is used to convert the DC voltage signal into a digital signal and send it to the host computer.

3. The capacitive cylinder block differential expansion measuring device for steam turbines according to claim 2, characterized in that, The high-pass filter circuit is a high-pass filter, the rectifier circuit is a bridge rectifier circuit, and the low-pass filter circuit is a low-pass filter.

4. The capacitive cylinder block differential expansion measuring device for steam turbines according to any one of claims 1 to 3, characterized in that, The host computer is also specifically used for: After outlier removal, the received DC signal is fed into a pre-trained deep learning model for prediction. The deep learning model uses an LSTM neural network architecture and is trained based on historical expansion data to predict the normal expansion range under the current operating conditions. When the deviation between the predicted value and the actual measured value exceeds the set threshold, it is judged as an abnormal state, and a risk warning signal is issued according to the degree of deviation.

5. The capacitive cylinder block differential expansion measuring device for steam turbines according to claim 4, characterized in that, The host computer is also specifically used for: The DC signal is subjected to outlier detection and removal using the Z-Score normalization method, and missing data is interpolated. The time-frequency characteristics and probability distribution characteristics of the signal are extracted using time-frequency analysis methods and variational autoencoders (VAEs). A timing prediction model is built based on an LSTM network, and the future output voltage value is predicted by a sliding window method. Establish a spatial vector representation model for four states: normal, slight abnormality, moderate abnormality, and severe abnormality; Real-time calculation of the spatial distance between current data characteristics and four states, and determination of device status based on the nearest neighbor principle; When an abnormal state is detected, an early warning signal of the corresponding level is triggered based on the level of abnormality.

6. The capacitive cylinder block differential expansion measuring device for steam turbines according to any one of claims 1 to 3, characterized in that, The conditioning circuit is arranged inside a shielded box, which is made of metal and is rigidly connected to the inside of the cylinder.

7. The capacitive cylinder block differential expansion measuring device for steam turbines according to any one of claims 1 to 3, characterized in that, The conditioning circuit is electrically connected to the first capacitor plate and the second capacitor plate via a shielded wire.

8. The capacitive cylinder block differential expansion measuring device for steam turbines according to any one of claims 1 to 3, characterized in that, The length of the first capacitor plate and the second capacitor plate ranges from 80mm to 100mm, and the width ranges from 30mm to 50mm.

Images