Thermal power plant noise and vibration monitoring method and system

Abstract

The invention discloses a thermal power plant noise and vibration monitoring method and system, and the method comprises the steps: obtaining the target part of thermal power plant equipment, and collecting the current monitoring data, one of the monitoring devices of the target part being located at the main body of the equipment, and the other being located at the key part of the equipment; constructing an equipment coordinate system of the thermal power plant equipment, and based on the position information of at least one feature data point set of the monitoring data, respectively determining a feature parameter difference value between each feature data point set in the monitoring data and the reference data model; determining a comprehensive characteristic index between the equipment main body and the key component according to each characteristic parameter difference value; responding to the condition that the value of the comprehensive characteristic index between the equipment main body and the key component meets a preset condition, and starting related operation of the thermal power plant; wherein the monitoring data comprises noise data and vibration data. Through the mode, the noise and vibration monitoring data of the thermal power plant can be efficiently and accurately monitored, and the abnormal state of the equipment can be responded in time.

Description

Technical Field

[0001] The present application relates to the technical field of thermal power plant monitoring, and in particular to a method and system for monitoring noise and vibration in a thermal power plant. Background Art

[0002] With the increasing complexity of thermal power plant equipment and the increasing operating requirements, noise and vibration monitoring has become an important part of ensuring safe operation and environmental protection. Traditional noise and vibration monitoring methods usually rely on a single sensor or manual inspection, which makes it difficult to achieve real-time and continuous monitoring and is easily affected by environmental interference. Therefore, how to achieve efficient and accurate monitoring of thermal power plant monitoring data is a technical problem that needs to be solved urgently by those skilled in the art. Summary of the invention

[0003] The main technical problem solved by the present application is to provide a noise and vibration monitoring method and system for a thermal power plant, which can realize efficient and accurate monitoring of noise and vibration monitoring data of a thermal power plant.

[0004] In order to solve the above technical problems, a technical solution adopted in the present application is: to provide a noise and vibration monitoring method for a thermal power plant, the method comprising: acquiring monitoring data at the target part of the thermal power plant equipment at the current moment, wherein one of the monitoring devices at the target part is located in the equipment body, and the other is located in the key component of the equipment; constructing an equipment coordinate system for the thermal power plant equipment, and based on the position information of at least one characteristic data point set in the monitoring data, respectively determining the characteristic parameter difference values ​​between each characteristic data point set in the monitoring data and the reference data model; determining the comprehensive characteristic index between the equipment body and the key component according to the difference values ​​of each characteristic parameter; in response to the numerical value of the comprehensive characteristic index between the equipment body and the key component satisfying a preset condition, starting the relevant operation of the thermal power plant; wherein the monitoring data includes noise data and vibration data.

[0005] The method further includes: respectively obtaining original monitoring data collected from several preset parts of the thermal power plant equipment; for the original monitoring data of each preset part, based on the position information of at least one feature data set in the original monitoring data, respectively determining the original feature parameter difference values ​​between each feature data set in the original monitoring data and a preset reference data model in the original monitoring data; calculating the standard deviation of each original feature parameter difference value corresponding to each preset part to obtain the standard deviation feature index corresponding to the preset part; and determining the preset part whose standard deviation feature index meets the feature index condition as the target part.

[0006] Among them, the monitoring data is obtained by preset processing of the current frame data; the monitoring data of the target part of the thermal power plant equipment is obtained at the current moment, including: sampling each data point of the current frame data to obtain multiple sampled data points; determining the characteristic value of each sampled data point according to the characteristic amplitude of each sampled data point; determining the monitoring data based on the position information of the target part and the characteristic value of each sampled data point.

[0007] Wherein, based on the location information of the target part and the characteristic value of each sampling data point, the monitoring data is determined, including: according to the location information of the target part, determining the candidate data points belonging to the target part from the sampling data points; obtaining the floating-point data corresponding to the candidate data points; for each candidate data point, determining the monitoring data of the candidate data point according to the reference data corresponding to the candidate data point, the characteristic value of the candidate data point, and the characteristic value of at least one adjacent candidate data point; wherein the reference data is obtained based on the coordinate value and floating-point data in the location information of the candidate data point.

[0008] Among them, at least one adjacent candidate data point of each candidate data point includes a first adjacent candidate data point, a second adjacent candidate data point and a third adjacent candidate data point, which are located in different directions of the corresponding position information of the candidate data point, and the reference data includes a reference horizontal coordinate value related to the horizontal coordinate of the candidate data point and a reference vertical coordinate value related to the vertical coordinate of the candidate data point; for each candidate data point, the monitoring data of the candidate data point is determined according to the reference data corresponding to the candidate data point, the characteristic value of the candidate data point, and the characteristic value of at least one adjacent candidate data point, including: determining the first monitoring characteristic data based on the reference horizontal coordinate value, the reference vertical coordinate value and the characteristic value of the candidate data point; determining the second monitoring characteristic data based on the reference horizontal coordinate value, the reference vertical coordinate value and the characteristic value of the first adjacent data point; determining the third monitoring characteristic data based on the reference horizontal coordinate value, the reference vertical coordinate value and the characteristic value of the second adjacent data point; determining the fourth monitoring characteristic data based on the reference horizontal coordinate value, the reference vertical coordinate value and the characteristic value of the third adjacent data point; combining the first monitoring characteristic data, the second monitoring characteristic data, the third monitoring characteristic data and the fourth monitoring characteristic data to obtain the monitoring characteristic data of the candidate data point.

[0009] Among them, the first monitoring characteristic data is the product of the first product value and the characteristic value of the candidate data point, wherein the first product is the product of the first transformation value and the second transformation value, and the sum value between the first transformation value and the reference horizontal coordinate value is equal to the sum value between the second transformation value and the reference vertical coordinate value; the second monitoring characteristic data is the product of the second product value and the characteristic value of the first adjacent data point, and the second product value is the product between the reference horizontal coordinate value and the second transformation value; the third monitoring characteristic data is the product of the third product value and the characteristic value of the second adjacent data point, and the third product value is the product between the first transformation value and the reference vertical coordinate value; the fourth monitoring characteristic data is the product of the fourth product value and the characteristic value of the third adjacent data point, and the fourth product value is the product between the reference horizontal coordinate value and the reference vertical coordinate value.

[0010] The method further includes: extracting features from monitoring data according to at least one of several preset feature extraction algorithms to obtain several feature data sets; and determining each feature data set for analysis based on the several feature data sets.

[0011] Wherein, based on several feature data sets, each feature data set for analysis is determined, including: determining the set range mean corresponding to several feature data sets; retaining the feature data sets that do not meet the set filtering conditions, obtaining at least one retained feature data set, and using each retained set as each feature data set for analysis; wherein the set filtering conditions include a first set filtering condition and / or a second set filtering condition, the first set filtering condition includes that the range of the feature data set is less than the set range mean; the second set filtering condition includes that the key eigenvalue of the feature data set is less than the threshold eigenvalue, and the threshold eigenvalue is the sum of the set range mean and the offset.

[0012] Among them, the preset feature extraction algorithms include Fourier transform and wavelet transform.

[0013] In order to solve the above technical problems, another technical solution adopted by the present application is: to provide a noise and vibration monitoring system for a thermal power plant, including a data acquisition module, a characteristic parameter determination module, a state determination module and a response module. Data acquisition module: used to acquire the current monitoring data collected from the target part of the thermal power plant equipment, wherein one of the monitoring devices of the target part is in the main body of the equipment, and the other is in the key component of the equipment; characteristic parameter determination module: used to construct the equipment coordinate system of the thermal power plant equipment, based on the position information of at least one characteristic data point set of the monitoring data, respectively determine the characteristic parameter difference value between each characteristic data point set in the monitoring data and the reference data model; state determination module: used to determine the comprehensive characteristic index between the main body of the equipment and the key component according to the difference value of each characteristic parameter; response module: used to start the relevant operation of the thermal power plant in response to the value of the comprehensive characteristic index between the main body of the equipment and the key component meeting the preset conditions; wherein the monitoring data includes noise data and vibration data.

[0014] Different from the prior art, the beneficial effects of the present application are as follows: the present application forms a spatial complementary data acquisition network by respectively setting up monitoring devices on the equipment body and key components to obtain monitoring data including noise data and vibration data at the current moment, and by constructing an equipment coordinate system, determines the characteristic parameter difference value of the reference data model based on the position information of the characteristic data point set of the monitoring data, and then determines the comprehensive characteristic index between the equipment body and the key components based on the difference value, and starts the relevant operation when the comprehensive characteristic index meets the preset conditions, thereby realizing efficient and accurate monitoring of the noise and vibration monitoring data of the thermal power plant and timely responding to abnormal equipment conditions. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flow chart of an implementation method of a thermal power plant noise and vibration monitoring method of the present application.

[0016] Figure 2 It is a schematic diagram of the structural framework of an implementation method of a noise and vibration monitoring system for a thermal power plant of the present application. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and effect of the present application clearer and more specific, the present application is further described in detail below with reference to the accompanying drawings and examples.

[0018] The term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the objects associated before and after are in an "or" relationship. In addition, "many" in this article means two or more than two. In addition, the term "at least one" in this article means any combination of at least two of any one or more of a variety, for example, including at least one of A, B, and C, and can mean including any one or more elements selected from the set consisting of A, B, and C. In addition, the terms "first" and "second" are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" can explicitly or implicitly include at least one of the features.

[0019] See also Figure 1 , Figure 1 Schematic diagram of a method for monitoring noise and vibration in a thermal power plant according to an embodiment of the present invention. Figure 1 As shown, the method includes: Step S11: acquiring the target part of the thermal power plant equipment to collect the current moment monitoring data, wherein one of the monitoring devices of the target part is located in the equipment body, and the other is located in the key component of the equipment.

[0020] The monitoring data includes noise data and vibration data. Specifically, the monitoring data at the current moment can be the current frame data, or it can be the data obtained by pre-processing the current frame data. The monitoring device is used to monitor the vibration and noise data of the key components of the equipment relative to the main body of the equipment.

[0021] In some application scenarios, the target part is a main component of the equipment. In other application scenarios, determining the target part of the equipment may include: respectively obtaining the original monitoring data collected from several preset parts of the thermal power plant equipment; for the original monitoring data of each preset part, based on the position information of at least one feature data set in the original monitoring data, respectively determining the original feature parameter difference value between each feature data set in the original monitoring data and the preset reference data model in the original monitoring data; calculating the standard deviation of each original feature parameter difference value corresponding to each preset part, and obtaining the standard deviation feature index corresponding to the preset part; determining the preset part whose standard deviation feature index meets the feature index condition as the target part.

[0022] Specifically, each feature data set in the original monitoring data is obtained by extracting features from the original monitoring data. The feature index condition is that the standard deviation feature index corresponding to the preset part is the minimum standard deviation feature index. In this way, the part that best reflects the change in the operating status of the equipment can be selected as the monitoring target, thereby improving the accuracy and effectiveness of the monitoring.

[0023] In some embodiments, the monitoring data is obtained by preset processing of the current frame data; acquiring the monitoring data of the target part of the thermal power plant equipment at the current moment, including: sampling each data point of the current frame data to obtain multiple sampled data points; determining the characteristic value of each sampled data point according to the characteristic amplitude of each sampled data point; determining the monitoring data based on the position information of the target part and the characteristic value of each sampled data point.

[0024] Specifically, in the monitoring data of thermal power plants, for vibration data, the characteristic amplitude may be reflected as the amplitude of the vibration, that is, the maximum distance that deviates from the equilibrium position during the vibration process. If the vibration of the turbine blades is monitored, a larger vibration amplitude means that the blades vibrate more violently during operation, and there may be imbalance or other hidden faults. For noise data, the characteristic amplitude can be the range of sound intensity variation. For example, the noise generated by the operation of equipment in a thermal power plant, the fluctuation of its intensity is a characteristic amplitude. In the process of determining the monitoring data, by processing the sampled data points, the amount of data can be reduced and the efficiency of subsequent processing can be improved.

[0025] Step S12: constructing an equipment coordinate system of the thermal power plant equipment, and determining the characteristic parameter difference values ​​between each characteristic data point set in the monitoring data and the reference data model based on the position information of at least one characteristic data point set in the monitoring data.

[0026] Specifically, when monitoring the operation of thermal power plant equipment, the location information of the target part is crucial. Its common forms include coordinate information, area identification, and relative position information with equipment components. These forms can accurately locate the target part and help effectively monitor the equipment status. Taking the steam turbine as an example, the turbine axis may be used as the origin, the axial direction is one coordinate axis direction, and the radial direction is another coordinate axis direction. When monitoring the vibration of the turbine blades, the horizontal coordinates of the candidate data points are determined based on this coordinate system. This can directly reflect the position of each point on the blade relative to the axis, which is extremely critical for analyzing the vibration characteristics of the blade and determining whether there are hidden fault hazards. Through the horizontal coordinate, you can clearly understand the vibration conditions of different positions of the blade. If the vibration of the position corresponding to the horizontal coordinate is abnormal, you can quickly locate the problem area and provide an accurate basis for equipment maintenance.

[0027] In some specific embodiments, for complex equipment such as steam turbines, a three-dimensional coordinate system may be constructed with the axis of the steam turbine as the origin and the axial and radial axes as coordinate axes. In this coordinate system, the position information of the characteristic data point set will be presented in the form of coordinate values. Assuming that a certain characteristic data point set is used to monitor the vibration of the steam turbine blade, its position information may be expressed as (x, y, z). This set of coordinate values ​​​​clarifies the specific position of the set in the steam turbine space, which may correspond to a specific area on the blade. Through such precise spatial positioning, it is possible to clearly know the equipment part represented by the data, providing a basis for subsequent analysis. When analyzing vibration data, combined with its position information, it can be determined which part of the blade has abnormal vibration, and then determine the possible cause of the fault, such as whether the blade has problems such as wear and deformation. The position information of the characteristic data point set is not fixed, but changes dynamically with the operation of the equipment. When the equipment is operating normally, the position information of these data point sets changes relatively stably and presents a certain regularity. For example, during the normal operation of the fan, the characteristic data point set used to monitor the fan blades, its position information will change regularly with the rotation of the blades. Once a device fails, such as a broken or unbalanced blade, the regularity of the position information change of the characteristic data point set will be disrupted. By continuously monitoring the changes in this position information, abnormalities in the operating status of the equipment can be discovered in a timely manner. If the position information that originally changed regularly changes suddenly or fluctuates abnormally, this may indicate that there is a hidden danger of equipment failure, and timely inspection and maintenance are required to avoid further expansion of equipment failure.

[0028] In some embodiments, monitoring data is determined based on the location information of the target part and the characteristic value of each sampling data point, including: determining candidate data points belonging to the target part from the sampling data points according to the location information of the target part; obtaining floating-point data corresponding to the candidate data points; for each candidate data point, determining the monitoring data of the candidate data point according to the reference data corresponding to the candidate data point, the characteristic value of the candidate data point, and the characteristic value of at least one adjacent candidate data point; wherein the reference data is obtained based on the coordinate value and floating-point data in the location information of the candidate data point.

[0029] Specifically, each floating point data is used to represent the numerical value corresponding to the decimal position of the coordinate value corresponding to the horizontal coordinate and the vertical coordinate of each candidate data point; the monitoring feature data of each candidate data point is used as the feature data corresponding to the monitoring data. By considering the feature values ​​of adjacent candidate data points, the features of the monitoring data can be determined more accurately, thereby improving the quality of the monitoring data.

[0030] In some embodiments, at least one adjacent candidate data point of each candidate data point includes a first adjacent candidate data point, a second adjacent candidate data point, and a third adjacent candidate data point, which are located in different directions of the corresponding position information of the candidate data point, and the reference data includes a reference horizontal coordinate value related to the horizontal coordinate of the candidate data point and a reference vertical coordinate value related to the vertical coordinate of the candidate data point; for each candidate data point, the monitoring data of the candidate data point is determined according to the reference data corresponding to the candidate data point, the characteristic value of the candidate data point, and the characteristic value of at least one adjacent candidate data point, including: determining the first monitoring characteristic data based on the reference horizontal coordinate value, the reference vertical coordinate value, and the characteristic value of the candidate data point; determining the second monitoring characteristic data based on the reference horizontal coordinate value, the reference vertical coordinate value, and the characteristic value of the first adjacent data point; determining the third monitoring characteristic data based on the reference horizontal coordinate value, the reference vertical coordinate value, and the characteristic value of the second adjacent data point; determining the fourth monitoring characteristic data based on the reference horizontal coordinate value, the reference vertical coordinate value, and the characteristic value of the third adjacent data point; combining the first monitoring characteristic data, the second monitoring characteristic data, the third monitoring characteristic data, and the fourth monitoring characteristic data to obtain the monitoring characteristic data of the candidate data point. By integrating the characteristic values ​​of adjacent data points in multiple directions, the monitoring situation can be reflected more comprehensively, making the determined monitoring characteristic data more accurate.

[0031] In some embodiments, the first monitoring characteristic data is the product between the first product value and the characteristic value of the candidate data point, wherein the first product is the product between the first transformation value and the second transformation value, and the sum value between the first transformation value and the reference horizontal coordinate value is equal to the sum value between the second transformation value and the reference vertical coordinate value; the second monitoring characteristic data is the product between the second product value and the characteristic value of the first adjacent data point, and the second product value is the product between the reference horizontal coordinate value and the second transformation value; the third monitoring characteristic data is the product between the third product value and the characteristic value of the second adjacent data point, and the third product value is the product between the first transformation value and the reference vertical coordinate value; the fourth monitoring characteristic data is the product between the fourth product value and the characteristic value of the third adjacent data point, and the fourth product value is the product between the reference horizontal coordinate value and the reference vertical coordinate value. In this way, the weight of the characteristic value of each data point can be flexibly adjusted by adjusting parameters such as the first transformation value and the second transformation value, thereby improving the accuracy of the monitoring characteristic data.

[0032] In some embodiments, the method further includes: extracting features from the monitoring data according to at least one of several preset feature extraction algorithms to obtain several feature data sets; and determining each feature data set for analysis based on the several feature data sets. The preset feature extraction algorithms include Fourier transform, wavelet transform, etc. By combining multiple algorithms, the features of the monitoring data can be extracted more comprehensively.

[0033] In some embodiments, based on several feature data sets, each feature data set for analysis is determined, including: determining the set range mean corresponding to several feature data sets; retaining the feature data sets that do not meet the set screening conditions, obtaining at least one retained feature data set, and using each retained set as each feature data set for analysis; wherein the set screening conditions include a first set screening condition and / or a second set screening condition, the first set screening condition includes that the range of the feature data set is less than the set range mean; the second set screening condition includes that the key feature value of the feature data set is less than the threshold feature value, and the threshold feature value is the sum of the set range mean and the offset. By screening the feature data sets, interference information can be removed and the accuracy of the analysis can be improved.

[0034] Step S13: Determine the comprehensive characteristic index between the equipment body and the key components according to the difference values ​​of each characteristic parameter.

[0035] In some specific embodiments, step S13 includes: determining whether the number of characteristic parameter difference values ​​is greater than a second number; in response to the number of characteristic parameter difference values ​​being less than or equal to the second number, taking each characteristic parameter difference value as each candidate characteristic parameter difference value; or, in response to the number of characteristic parameter difference values ​​being greater than the second number, clustering each characteristic parameter difference value to obtain characteristic parameter difference values ​​corresponding to each clustering cluster; taking the characteristic parameter difference values ​​corresponding to each clustering cluster as each candidate characteristic parameter difference value. According to each candidate characteristic parameter difference value, determine the target comprehensive index between the equipment body and the key components. Through cluster analysis, a large number of initial characteristic parameter difference values ​​can be classified and processed to improve the accuracy of determining the operating status of the equipment.

[0036] Further, each candidate characteristic parameter difference value can be adjusted according to a reference condition to obtain an adjusted characteristic parameter difference value corresponding to each candidate characteristic parameter difference value, the reference condition includes a first reference condition and / or a second reference condition, the first reference condition includes adjusting the candidate characteristic parameter difference value less than a preset threshold value to a first fixed value, and the second reference condition includes taking the difference between the candidate characteristic parameter difference value greater than or equal to the preset threshold value and the second fixed value as the adjusted characteristic parameter difference value; based on each adjusted characteristic parameter difference value, determine the target comprehensive index. By adjusting the characteristic parameter difference value under the reference condition, the actual operating status of the device can be more accurately reflected.

[0037] In some specific embodiments, in response to the number of each adjusted characteristic parameter difference value being less than the first number, each adjusted characteristic parameter difference value can be determined as the target indicator; or, in response to the number of each adjusted characteristic parameter difference value being greater than or equal to the first number, the largest adjusted characteristic parameter difference value can be determined as the target indicator; in response to the target indicator being greater than or equal to the expected threshold, the target indicator can be determined as the value of the target comprehensive indicator, and the expected threshold is used to characterize the indicator value corresponding to the minimum comprehensive indicator between the device body and the key components when the device is in an abnormal operating state. By reasonably selecting the target indicator, the operating state of the device can be judged more accurately.

[0038] In some specific embodiments, in response to the target indicator being less than the expected threshold, a preset indicator is obtained; the preset indicator is determined as the value of the target comprehensive indicator. The preset indicator can be a pre-set comprehensive indicator value when the device is operating normally, which is used as a reference when the target indicator is abnormal.

[0039] In some embodiments, the indicator difference between the target comprehensive indicator and the historical comprehensive indicator can also be obtained, and the historical comprehensive indicator is the target comprehensive indicator between the equipment body and the key components determined based on the monitoring data collected at the historical moment; in response to the indicator difference being greater than or equal to the threshold difference, the historical comprehensive indicator is used as the final comprehensive indicator between the equipment body and the key components at the current moment; or, in response to the indicator difference being less than the threshold difference, the target comprehensive indicator is used as the final comprehensive indicator between the equipment body and the key components at the current moment. By comparing the current and historical comprehensive indicators, the changing trend of the equipment operation status can be judged more accurately.

[0040] Step S14: In response to the value of the comprehensive characteristic index between the equipment body and the key components satisfying the preset conditions, the relevant operations of the thermal power plant are started.

[0041] Specifically, during the operation of thermal power plant equipment, the change of equipment status is a relatively smooth process. If there is a large jump in the value of the final comprehensive index, it may be because an error occurred during the feature extraction or analysis process. At this time, an indicator fluctuation value is set. If the value change of the final comprehensive index in a certain period of time is greater than this fluctuation value, the value of the historical comprehensive index is used to determine whether to start the relevant operation, so that the value of the final comprehensive index determined is more in line with reality, so as to more accurately judge the equipment operation status and start the relevant operation in time. Relevant operations include but are not limited to starting standby equipment, issuing fault alarms, adjusting equipment operating parameters, etc. The preset condition can be that the value of the target comprehensive index is greater than or equal to the preset threshold, which is the minimum threshold when the equipment is in an abnormal operating state. When the target comprehensive index meets the preset condition, it means that the equipment may have hidden dangers of failure, and corresponding measures need to be taken in time to ensure the safe and stable operation of the thermal power plant.

[0042] In the above scheme, this application directly obtains the current moment monitoring data of the target part of the thermal power plant equipment, and constructs the equipment coordinate system to determine the characteristic parameter difference value between the monitoring data and the reference data model, and then determines the comprehensive characteristic indicators between the equipment body and key components. This method does not require complex encoding or conversion processing of the monitoring data, reduces the computing power required for data processing, and thus reduces the monitoring cost. At the same time, through feature extraction and screening, it can more accurately analyze the equipment status, respond to abnormal situations between the equipment body and key components in a timely manner, and improve the operating efficiency and safety of thermal power plants.

[0043] See also Figure 2 , Figure 2 Schematic diagram of the structural framework of an implementation method of the noise and vibration monitoring system for a thermal power plant of the present application. Figure 2 As shown, the noise and vibration monitoring system 20 of the thermal power plant includes a data acquisition module 21, a characteristic parameter determination module 22, a state determination module 23 and a response module 24. The data acquisition module 21 is used to acquire the monitoring data collected at the target part of the thermal power plant equipment at the current moment, wherein one of the monitoring devices of the target part is located in the main body of the equipment and the other is located in the key component of the equipment; the characteristic parameter determination module 22 is used to construct the equipment coordinate system of the thermal power plant equipment, and based on the position information of at least one characteristic data point set of the monitoring data, the characteristic parameter difference value between each characteristic data point set in the monitoring data and the reference data model is determined respectively; the state determination module 23 is used to determine the comprehensive characteristic index between the main body of the equipment and the key component according to each characteristic parameter difference value; the response module 24 is used to start the relevant operation of the thermal power plant in response to the value of the comprehensive characteristic index between the main body of the equipment and the key component meeting the preset condition; wherein the monitoring data includes noise data and vibration data.

[0044] In some embodiments, the data acquisition module 21 is also used to respectively acquire the original monitoring data collected from several preset parts of the thermal power plant equipment; for the original monitoring data of each preset part, based on the position information of at least one feature data set in the original monitoring data, respectively determine the original feature parameter difference values ​​between each feature data set in the original monitoring data and the preset reference data model in the original monitoring data; calculate the standard deviation of each original feature parameter difference value corresponding to each preset part, and obtain the standard deviation feature index corresponding to the preset part; the preset part whose standard deviation feature index meets the feature index condition is determined as the target part.

[0045] In some embodiments, the monitoring data is obtained by preset processing of the current frame data; the data acquisition module 21 obtains the monitoring data collected at the target part of the thermal power plant equipment at the current moment, including: sampling each data point of the current frame data to obtain multiple sampled data points; determining the characteristic value of each sampled data point according to the characteristic amplitude of each sampled data point; determining the monitoring data based on the position information of the target part and the characteristic value of each sampled data point.

[0046] In some embodiments, the data acquisition module 21 is also used to determine monitoring data based on the location information of the target part and the characteristic value of each sampling data point, including: determining the candidate data points belonging to the target part from the sampling data points according to the location information of the target part; acquiring the floating-point data corresponding to the candidate data points; for each candidate data point, determining the monitoring data of the candidate data point according to the reference data corresponding to the candidate data point, the characteristic value of the candidate data point, and the characteristic value of at least one adjacent candidate data point; wherein the reference data is obtained based on the coordinate value and floating-point data in the location information of the candidate data point.

[0047] Among them, at least one adjacent candidate data point of each candidate data point includes a first adjacent candidate data point, a second adjacent candidate data point and a third adjacent candidate data point, which are located in different directions of the corresponding position information of the candidate data point, and the reference data includes a reference horizontal coordinate value related to the horizontal coordinate of the candidate data point and a reference vertical coordinate value related to the vertical coordinate of the candidate data point; for each candidate data point, the monitoring data of the candidate data point is determined according to the reference data corresponding to the candidate data point, the characteristic value of the candidate data point, and the characteristic value of at least one adjacent candidate data point, including: determining the first monitoring characteristic data based on the reference horizontal coordinate value, the reference vertical coordinate value and the characteristic value of the candidate data point; determining the second monitoring characteristic data based on the reference horizontal coordinate value, the reference vertical coordinate value and the characteristic value of the first adjacent data point; determining the third monitoring characteristic data based on the reference horizontal coordinate value, the reference vertical coordinate value and the characteristic value of the second adjacent data point; determining the fourth monitoring characteristic data based on the reference horizontal coordinate value, the reference vertical coordinate value and the characteristic value of the third adjacent data point; combining the first monitoring characteristic data, the second monitoring characteristic data, the third monitoring characteristic data and the fourth monitoring characteristic data to obtain the monitoring characteristic data of the candidate data point.

[0048] Among them, the first monitoring characteristic data is the product of the first product value and the characteristic value of the candidate data point, wherein the first product is the product of the first transformation value and the second transformation value, and the sum value between the first transformation value and the reference horizontal coordinate value is equal to the sum value between the second transformation value and the reference vertical coordinate value; the second monitoring characteristic data is the product of the second product value and the characteristic value of the first adjacent data point, and the second product value is the product between the reference horizontal coordinate value and the second transformation value; the third monitoring characteristic data is the product of the third product value and the characteristic value of the second adjacent data point, and the third product value is the product between the first transformation value and the reference vertical coordinate value; the fourth monitoring characteristic data is the product of the fourth product value and the characteristic value of the third adjacent data point, and the fourth product value is the product between the reference horizontal coordinate value and the reference vertical coordinate value.

[0049] In some embodiments, the feature parameter determination module 22 is further used to extract features from the monitoring data according to at least one of several preset feature extraction algorithms to obtain several feature data sets; based on the several feature data sets, determine each feature data set for analysis. Among them, the preset feature extraction algorithms include Fourier transform and wavelet transform.

[0050] In some embodiments, the feature parameter determination module 22 is also used to determine each feature data set for analysis based on several feature data sets, including: determining the set range mean corresponding to several feature data sets; retaining the feature data sets that do not meet the set filtering conditions to obtain at least one retained feature data set, and using each retained set as each feature data set for analysis; wherein the set filtering conditions include a first set filtering condition and / or a second set filtering condition, the first set filtering condition includes that the range of the feature data set is less than the set range mean; the second set filtering condition includes that the key feature value of the feature data set is less than the threshold feature value, and the threshold feature value is the sum of the set range mean and the offset.

[0051] In the above scheme, this application directly obtains the current moment monitoring data of the target part of the thermal power plant equipment, and constructs the equipment coordinate system to determine the characteristic parameter difference value between the monitoring data and the reference data model, and then determines the comprehensive characteristic indicators between the equipment body and key components. This method does not require complex encoding or conversion processing of the monitoring data, reduces the computing power required for data processing, and thus reduces the monitoring cost. At the same time, through feature extraction and screening, it can more accurately analyze the equipment status, respond to abnormal situations between the equipment body and key components in a timely manner, and improve the operating efficiency and safety of thermal power plants.

[0052] The above description is only an implementation method of the present application and does not limit the scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the protection scope of the present application.

Claims

1. A method for monitoring noise and vibration in a thermal power plant, characterized in that: The method comprises: acquiring monitoring data collected at the current moment from a target part of thermal power plant equipment, wherein one of the monitoring devices of the target part is located in the equipment body and the other is located in a key component of the equipment; constructing an equipment coordinate system of the thermal power plant equipment, and determining the characteristic parameter difference values ​​between each characteristic data point set in the monitoring data and a reference data model based on the position information of at least one characteristic data point set of the monitoring data; determining the comprehensive characteristic index between the equipment body and the key component according to the difference values ​​of each characteristic parameter; and starting the relevant operation of the thermal power plant in response to the value of the comprehensive characteristic index between the equipment body and the key component satisfying a preset condition; wherein the monitoring data comprises noise data and vibration data.

2. The noise and vibration monitoring method for a thermal power plant according to claim 1, characterized in that: The method also includes: respectively obtaining original monitoring data collected from several preset parts of the thermal power plant equipment; for the original monitoring data of each preset part, based on the position information of at least one feature data set in the original monitoring data, respectively determining the original feature parameter difference values ​​between each feature data set in the original monitoring data and a preset reference data model in the original monitoring data; calculating the standard deviation of each original feature parameter difference value corresponding to each preset part to obtain the standard deviation feature index corresponding to the preset part; and determining the preset part whose standard deviation feature index meets the feature index condition as the target part.

3. The noise and vibration monitoring method for a thermal power plant according to claim 2, characterized in that: The monitoring data is obtained by pre-processing the current frame data; The method of acquiring the current monitoring data of the target part of the thermal power plant equipment includes: sampling each data point of the current frame data to obtain a plurality of sampled data points; determining the characteristic value of each sampled data point according to the characteristic amplitude of each sampled data point; and determining the monitoring data based on the position information of the target part and the characteristic value of each sampled data point.

4. The noise and vibration monitoring method for a thermal power plant according to claim 3, characterized in that: The method of determining monitoring data based on the position information of the target part and the characteristic value of each sampling data point includes: determining candidate data points belonging to the target part from the sampling data points according to the position information of the target part; obtaining floating-point data corresponding to the candidate data points; for each candidate data point, determining monitoring data of the candidate data point according to reference data corresponding to the candidate data point, the characteristic value of the candidate data point, and the characteristic value of at least one adjacent candidate data point; wherein the reference data is obtained based on the coordinate value and floating-point data in the position information of the candidate data point.

5. The noise and vibration monitoring method for a thermal power plant according to claim 4, characterized in that: At least one adjacent candidate data point of each candidate data point includes a first adjacent candidate data point, a second adjacent candidate data point, and a third adjacent candidate data point, which are located in different directions of the corresponding position information of the candidate data point, and the reference data includes a reference abscissa value associated with the abscissa of the candidate data point and a reference ordinate value associated with the ordinate of the candidate data point; The step of determining, for each candidate data point, monitoring data of the candidate data point according to reference data corresponding to the candidate data point, a feature value of the candidate data point, and a feature value of at least one adjacent candidate data point comprises: determining first monitoring feature data based on the reference abscissa value, the reference ordinate value, and the feature value of the candidate data point; Based on the reference horizontal coordinate value, the reference vertical coordinate value and the characteristic value of the first adjacent data point, the second monitoring feature data is determined; based on the reference horizontal coordinate value, the reference vertical coordinate value and the characteristic value of the second adjacent data point, the third monitoring feature data is determined; based on the reference horizontal coordinate value, the reference vertical coordinate value and the characteristic value of the third adjacent data point, the fourth monitoring feature data is determined; and the monitoring feature data of the candidate data point is obtained by combining the first monitoring feature data, the second monitoring feature data, the third monitoring feature data and the fourth monitoring feature data.

6. The method for monitoring noise and vibration in a thermal power plant according to claim 5, characterized in that: The first monitoring characteristic data is the product of a first product value and a characteristic value of the candidate data point, wherein the first product is the product of a first transformation value and a second transformation value, and the sum of the first transformation value and the reference horizontal coordinate value is equal to the sum of the second transformation value and the reference vertical coordinate value; the second monitoring characteristic data is the product of a second product value and a characteristic value of the first adjacent data point, and the second product value is the product of the reference horizontal coordinate value and the second transformation value; the third monitoring characteristic data is the product of a third product value and a characteristic value of the second adjacent data point, and the third product value is the product of the first transformation value and the reference vertical coordinate value; the fourth monitoring characteristic data is the product of a fourth product value and a characteristic value of the third adjacent data point, and the fourth product value is the product of the reference horizontal coordinate value and the reference vertical coordinate value.

7. The method for monitoring noise and vibration in a thermal power plant according to claim 1 or 6, characterized in that: The method further includes: extracting features from the monitoring data according to at least one of several preset feature extraction algorithms to obtain several feature data sets; and determining each feature data set for analysis based on the several feature data sets.

8. The method for monitoring noise and vibration in a thermal power plant according to claim 7, characterized in that: Determining each of the feature data sets for analysis based on the plurality of feature data sets includes: determining a set range mean corresponding to the plurality of feature data sets; retaining feature data sets that do not satisfy a set screening condition to obtain at least one retained feature data set, and using each retained set as each of the feature data sets for analysis; wherein the set screening condition includes a first set screening condition and / or a second set screening condition, the first set screening condition including that the range of the feature data set is less than the set range mean; the second set screening condition including that the key eigenvalue of the feature data set is less than a threshold eigenvalue, the threshold eigenvalue being the sum of the set range mean and an offset.

9. The method for monitoring noise and vibration in a thermal power plant according to claim 8, characterized in that: The preset feature extraction algorithm includes Fourier transform and wavelet transform.

10. A noise and vibration monitoring system for a thermal power plant, characterized in that: include: Data acquisition module: used to acquire the current monitoring data collected from the target part of the thermal power plant equipment, wherein one of the monitoring devices of the target part is located in the equipment body, and the other is located in the key component of the equipment; characteristic parameter determination module: used to construct the equipment coordinate system of the thermal power plant equipment, and based on the position information of at least one characteristic data point set of the monitoring data, respectively determine the characteristic parameter difference value between each characteristic data point set in the monitoring data and the reference data model; state determination module: used to determine the comprehensive characteristic index between the equipment body and the key component according to the difference value of each characteristic parameter; response module: used to start the relevant operation of the thermal power plant in response to the value of the comprehensive characteristic index between the equipment body and the key component meeting the preset condition; wherein the monitoring data includes noise data and vibration data.

Images