A bearing temperature monitoring method for a large fluid machine starting process

Abstract

The application provides a bearing temperature monitoring method for a large fluid machine starting process, comprising: obtaining a state vector and constructing a time window vector by using a sliding time window; selecting uniformly distributed time window vectors for model construction by calculating the distance between the time window vectors; obtaining the output of the model by vector distance analysis on the state vector of the monitoring period; and constructing a bearing temperature early warning vector based on the reconstruction output of the continuous monitoring time, so as to realize bearing temperature monitoring. The application can effectively monitor the bearing temperature of the large fluid machine during the starting process, and timely early warning when there is a fault risk, and has high accuracy and sensitivity.

Description

Technical Field

[0001] This invention relates to a bearing temperature monitoring method during the start-up process of large fluid machinery, and in particular to a bearing temperature monitoring method during the start-up process of large fluid machinery based on sliding time window operation, vector distance analysis and early warning logic construction. Background Technology

[0002] Large fluid machinery such as pumps, compressors, and fans are key equipment in the industrial field, and their bearing temperature is an important parameter reflecting the operating status of the equipment. During startup, as mechanical components accelerate from a stationary state to rated speed, the bearings bear significant frictional and impact loads, resulting in significant temperature changes. If the bearing temperature rises abnormally, it may lead to lubrication failure, material wear, or even equipment damage, thereby causing downtime and affecting production safety and efficiency.

[0003] Currently, bearing temperature monitoring methods mainly rely on traditional threshold alarm methods. These methods are typically based on fixed thresholds or simple trend analysis, triggering an alarm when the bearing temperature exceeds a preset threshold. However, traditional methods have the following limitations: 1) Fixed threshold methods cannot effectively capture subtle changes in bearing temperature, potentially leading to delayed or missed alarms; 2) The start-up process of large fluid machinery is affected by various factors (such as load changes, ambient temperature, etc.), making it difficult for traditional methods to dynamically adapt to temperature changes under different operating conditions; 3) Traditional methods typically only focus on the temperature value at a single point in time, ignoring the changing patterns of bearing temperature over time, and thus failing to comprehensively reflect the equipment status.

[0004] Therefore, there is an urgent need to develop a new monitoring method that can effectively address the above limitations, improve the accuracy and sensitivity of bearing temperature monitoring during the start-up process of large fluid machinery, and provide strong support for the safe operation of industrial equipment. Summary of the Invention

[0005] The purpose of this invention is to provide a bearing temperature monitoring method for the start-up process of large fluid machinery based on sliding time window operation, vector distance analysis, and early warning logic. This method aims to overcome some limitations in the existing technology and improve the accuracy and sensitivity of bearing temperature monitoring during the start-up process of fluid machinery.

[0006] To achieve the above objectives, the technical solution provided by the present invention is as follows:

[0007] A method for monitoring bearing temperature during the start-up process of large fluid machinery, the temperature monitoring method being based on sliding time window operation, vector distance analysis, and early warning logic construction, includes the following steps:

[0008] S1. Collect bearing temperature data during the start-up process of fluid machinery to obtain multiple state vectors. Use the state vectors under safe operating conditions to form the model database for the monitoring method.

[0009] S2. Apply a sliding time window operation to the state vectors in the model database to obtain multiple time window vectors;

[0010] S3. Calculate the distance between time window vectors, select uniformly distributed time window vectors to form a memory matrix, and obtain the distance matrix of the memory matrix to complete the model construction;

[0011] S4. During the monitoring period, the state vector corresponding to the bearing temperature during the start-up process of the fluid machinery is subjected to time window operation to obtain the monitoring time window vector, which is used as the input of the model; the distance between the monitoring time window vector and the time window vector in the memory matrix is ​​calculated to obtain the distance vector; the model reconstruction output is obtained through vector distance analysis.

[0012] S5. After obtaining the reconstructed output of multiple continuous monitoring time window vectors, the bearing temperature is monitored during the start-up process of large fluid machinery based on the bearing temperature early warning vector and the monitoring and early warning logic.

[0013] Preferably, step S1 specifically includes the following steps:

[0014] S101. During the start-up process of the fluid machinery, bearing temperature data is collected; the bearing temperature data collected each time is used to construct a state vector, as follows:

[0015] ，

[0016] in, Indicates the sampling time index. This indicates the number of measuring points for bearing temperature. express The state vector at time t, They represent the first Each bearing temperature measuring point is at Data at any given time;

[0017] S102. The state vector under the safe start-up condition of fluid machinery is incorporated into the model database of the monitoring method for model construction.

[0018] Preferably, step S2 specifically includes the following steps:

[0019] S201. Apply a time window operation to the state vectors in the model database to obtain the following time window vectors:

[0020] ,

[0021] in, This indicates the length of the time window. Represents the time window vector. They represent the first Each bearing temperature measuring point is at

[0022] The time window data corresponding to each moment is as follows:

[0023] ，

[0024] in, ;

[0025] S202. Slide the execution of step S201 on the time axis to obtain multiple time window vectors, denoted as... subscript This indicates the number of time window vectors obtained in this step.

[0026] Preferably, step S3 specifically includes the following steps:

[0027] S301. Calculate the distance between any two time window vectors, as follows:

[0028] ,

[0029] in, , represents the time index of the time window vector. , Represents the two time window vectors involved in the distance calculation. , They represent the first Each bearing temperature measuring point is at and Time window data corresponding to a given moment The Euclidean norm of a vector;

[0030] S302. By maximizing the minimum distance operation, the time window vectors obtained in step S202 are filtered, and the memory matrix is ​​constructed as follows:

[0031] ，

[0032] in, Represents the memory matrix, This indicates the number of time window vectors obtained after filtering. The mapping representing the filtering satisfies and set The model is ;

[0033] S303. Construct the distance matrix corresponding to the memory matrix. The distance matrix is The square matrix is ​​as follows:

[0034] ,

[0035] Among them, index .

[0036] To further explain, in step S302, let The set of time window vectors is represented as We need to select from them. A subset is formed by time window vectors. The minimum distance maximization method requires:

[0037] ,

[0038] This operation maximizes the minimum distance to ensure that the selected time window vectors are as uniform as possible, avoiding excessive density or overlap, i.e., too small a distance.

[0039] Preferably, step S4 specifically includes the following steps:

[0040] S401. During the startup process of the fluid machinery in the monitoring period, collect bearing temperature data; construct a state vector from the monitored bearing temperature data, as follows:

[0041] ，

[0042] in, This indicates the index of the sampling time within the monitoring period. express The state vector at time t, They represent the first Each bearing temperature measuring point is at Data at any given time;

[0043] S402. Repeat step S401 during the monitoring period. Based on the obtained multiple state vectors, use a time window operation to obtain a monitoring time window vector as the input to the model, as follows:

[0044] ,

[0045] in, Represents the monitoring time window vector. They represent the first Each bearing temperature measuring point is at The time window data corresponding to each moment is as follows:

[0046] ，

[0047] S403, Input of Calculation Model With memory matrix The distances between the vectors within the intermediate time windows are represented by the following distance vectors:

[0048] ,

[0049] in, Represents the distance vector. Represents the monitoring time window vector With time window vector The distance is as follows:

[0050] ,

[0051] S404. Based on vector distance analysis, the model outputs a monitoring time window vector. The monitoring results are as follows:

[0052] ，

[0053] in, The representation model is for The output reconstruction result, scale coefficient Make The sum of the elements is 1.

[0054] To further explain, in step S404, let Therefore, the monitoring results can be rewritten in the following form:

[0055] ，

[0056] Monitoring results output by the model It is a weighted sum of the time window vectors in the memory matrix, and the weight vector is... It reflects the proportion of each time window vector in the reconstructed monitoring results.

[0057] Preferably, step S5 specifically includes the following steps:

[0058] S501, Results from Model Output extract The reconstructed state vector at time step is as follows:

[0059] ，

[0060] in, This indicates the model output in The first state vector reconstructed at time step 1. The first output of the model represents the... Each measuring point is at The first reconstructed value of the time-series data;

[0061] S502, Time Setting Repeat step S4 to extract. The reconstructed state vectors at time t = ... Moment Reconstructed state vectors ;

[0062] S503, High Bearing Temperature Warning Vector and low warning vector as follows:

[0063] ,

[0064] in Indicates an index;

[0065] S504, for fluid machinery The first moment Temperature measurement points of each bearing To perform monitoring, set the bearing temperature monitoring deviation value according to the following rules:

[0066] ,

[0067] in, , These represent the early warning vectors. , The Each element value; the deviation value indicates the temperature. Deviating from the safe range The degree of deviation is assessed, and warning thresholds are set for the deviation values. Warnings are set according to the degree of deviation, and multi-level warnings are implemented.

[0068] S505. For the remaining times during the monitoring period, execute steps S501, S502, S503, and S504 of steps S4 and S5 to obtain the monitoring results for the monitoring period, thereby realizing the monitoring of bearing temperature during the start-up process of large fluid machinery.

[0069] To further explain, since the time window length is Therefore, the model's reconstruction result of the monitoring time window vector output includes Information from consecutive moments, i.e., the reconstruction result at a certain monitoring moment, will appear in In each monitoring time point, step S4 is repeated for multiple time points in step S502, i.e., in order to collect model data... Moment A reconstructed state vector; in step S503, based on The upper and lower bounds of the reconstructed state vectors define the warning vectors.

[0070] Compared with the prior art, the present invention has the following advantages:

[0071] This invention significantly improves the accuracy and sensitivity of bearing temperature monitoring during the start-up process of large fluid machinery by employing sliding time window operation, vector distance analysis, and early warning logic. The sliding time window dynamically captures temperature change patterns, vector distance analysis quantifies data similarity, and adaptive early warning logic enhances monitoring adaptability, comprehensively reflecting the equipment status. This method reduces false alarm and false negative rates, enabling early warning and providing valuable time for equipment maintenance, effectively preventing equipment failures. This invention offers high precision and high sensitivity, providing reliable support for the safety monitoring of large industrial fluid machinery. Attached Figure Description

[0072] Figure 1 A flowchart illustrating the process of monitoring bearing temperature during the start-up of large fluid machinery provided by this invention;

[0073] Figure 2 This is a flowchart illustrating the process of filtering time window vectors using the minimum distance maximization method in step S3.

[0074] Figure 3 This is a schematic diagram of the data from a certain temperature measuring point and the safe range output by the model during bearing temperature monitoring under safe start-up conditions, according to an embodiment of the present invention.

[0075] Figure 4 This is a schematic diagram of the monitoring deviation value and multi-level early warning interval in the bearing temperature monitoring task under safe start-up conditions according to an embodiment of the present invention;

[0076] Figure 5 This is a schematic diagram of the data from an abnormal temperature measurement point and the safe range of the model output during a bearing temperature monitoring task under a fault-prone start-up condition, according to an embodiment of the present invention.

[0077] Figure 6 This is a schematic diagram of the monitoring deviation value of an abnormal temperature measuring point and the multi-level early warning interval in a bearing temperature monitoring task under a fault-prone start-up condition according to an embodiment of the present invention. Detailed Implementation

[0078] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. However, the present invention can be implemented in many other ways different from those described herein, and those skilled in the art can make similar modifications without departing from the spirit of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0079] The example selected in this embodiment is an auxiliary feedwater pump of a nuclear power plant in China, such as... Figure 1 The diagram illustrates the workflow of the auxiliary feedwater pump start-up bearing temperature monitoring method based on sliding time window operation, vector distance analysis, and early warning logic in this embodiment. The steps in this embodiment are described below.

[0080] S1. Collect bearing temperature data during the start-up process of the auxiliary feedwater pump to obtain multiple state vectors. Use these state vectors under safe operating conditions to form the model database for the monitoring method. Specifically, this includes the following steps:

[0081] S101. During the start-up process of the auxiliary feedwater pump, bearing temperature data is collected; the bearing temperature data collected each time is used to construct a state vector, as follows:

[0082] ，

[0083] in, Indicates the sampling time index. This indicates the number of measuring points for bearing temperature. express The state vector at time t, They represent the first Each bearing temperature measuring point is at Data at any given moment.

[0084] In this embodiment, the number of bearing temperature measuring points of the auxiliary water pump is... .

[0085] S102. The state vector of the auxiliary water pump under safe start-up conditions is incorporated into the model database of the monitoring method for model construction.

[0086] Step S2: Apply a sliding time window operation to the state vectors in the model database to obtain multiple time window vectors. This specifically includes the following steps:

[0087] S201. Apply a time window operation to the state vectors in the model database. In this embodiment, the length of the time window is 10 time points, resulting in the following time window vector:

[0088] ,

[0089] in, Represents the time window vector. They represent the first Each bearing temperature measuring point is at The time window data corresponding to each moment is as follows:

[0090] ，

[0091] in, .

[0092] S202. Slide the execution of step S201 on the time axis. In this embodiment, 2000 time window vectors are obtained, denoted as... .

[0093] Step S3: Calculate the distance between time window vectors, select uniformly distributed time window vectors to construct a memory matrix, and obtain the distance matrix of the memory matrix to complete the model construction. Specifically, this includes the following steps:

[0094] S301. Calculate the distance between any two time window vectors, as follows:

[0095] ,

[0096] in, , represents the time index of the time window vector. , Represents the two time window vectors involved in the distance calculation. , They represent the first Each bearing temperature measuring point is at and Time window data corresponding to a given moment This represents the Euclidean norm of a vector.

[0097] S302. In this embodiment, by maximizing the minimum distance operation, a total of 1000 time window vectors obtained in step S202 are filtered, and a memory matrix is ​​constructed as follows:

[0098] ，

[0099] in, Represents the memory matrix, The mapping representing the filtering operation satisfies and set The model is .

[0100] The workflow diagram for filtering time window vectors using the minimum distance maximization method is as follows: Figure 2 As shown.

[0101] S303. Construct the distance matrix corresponding to the memory matrix. The distance matrix is The square matrix is ​​as follows:

[0102] ,

[0103] Among them, index .

[0104] Step S4: During the monitoring period, perform a time window operation on the state vector corresponding to the bearing temperature during the auxiliary feedwater pump start-up process to obtain the monitoring time window vector, which serves as the input to the model; calculate the distance between the monitoring time window vector and the time window vector in the memory matrix to obtain the distance vector; and obtain the reconstructed output of the model through vector distance analysis. Specifically, this includes the following steps:

[0105] S401. During the start-up process of the auxiliary feedwater pump in the monitoring period, collect bearing temperature data; construct a state vector from the monitored bearing temperature data, as follows:

[0106] ，

[0107] in, This indicates the index of the sampling time within the monitoring period. express The state vector at time t, They represent the first Each bearing temperature measuring point is at Data at any given moment.

[0108] S402. Repeat step S401 during the monitoring period. Based on the obtained multiple state vectors, use a time window operation to obtain a monitoring time window vector as the input to the model, as follows:

[0109] ,

[0110] in, Represents the monitoring time window vector. They represent the first Each bearing temperature measuring point is at The time window data corresponding to each moment is as follows:

[0111] ，

[0112] S403, Input of Calculation Model With memory matrix The distances between the vectors within the intermediate time windows are represented by the following distance vectors:

[0113] ,

[0114] in, Represents the distance vector. Represents the monitoring time window vector With time window vector The distance is as follows:

[0115] ,

[0116] S404. Based on vector distance analysis, the model outputs a monitoring time window vector. The monitoring results are as follows:

[0117] ，

[0118] in, The representation model is for The output reconstruction result, scale coefficient Make The sum of the elements is 1.

[0119] Step S5: After obtaining the reconstructed output of multiple continuous monitoring time window vectors, the bearing temperature is monitored during the start-up process of large fluid machinery based on the bearing temperature early warning vector and monitoring and early warning logic. Specifically, this includes the following steps:

[0120] S501, Results from Model Output extract The reconstructed state vector at time step is as follows:

[0121] ，

[0122] in, This indicates the model output in The first state vector reconstructed at time step 1. These represent the first output of the model, respectively. Each measuring point is at The first reconstructed value of the time-based data.

[0123] S502, Time Setting Repeat step S4 to extract. The reconstructed state vectors at time t = ... 10 reconstructed state vectors at time 10 .

[0124] S503, High Bearing Temperature Warning Vector and low warning vector as follows:

[0125] ,

[0126] in Indicates an index.

[0127] S504, Regarding the auxiliary water supply pump The first moment Temperature measurement points of each bearing To perform monitoring, set the bearing temperature monitoring deviation value according to the following rules:

[0128] ,

[0129] in, , These represent the early warning vectors. , The Each element value; the deviation value indicates the temperature. Deviating from the safe range The degree of deviation can be assessed by setting early warning thresholds for the deviation value, and setting early warnings according to the degree of deviation, thus implementing multi-level early warning.

[0130] In this embodiment, the rules for issuing warnings are as follows:

[0131] ,

[0132] S505. For the remaining times during the monitoring period, execute steps S4 and S501, S502, S503, and S504 of step S5 to obtain the monitoring results for the monitoring period, thereby realizing the monitoring of the bearing temperature of the auxiliary feedwater pump in the nuclear power plant during the start-up process.

[0133] In this embodiment, during the task of monitoring the bearing temperature at a certain measuring point under the safe start-up condition of the auxiliary feedwater pump, the interval results are as follows: Figure 3 As shown, the monitoring deviation value of this measuring point is as follows: Figure 4 As shown; During the task of monitoring the bearing temperature at a certain measuring point when the auxiliary feedwater pump is started under conditions of potential failure, the interval results are as follows: Figure 5 As shown, the monitoring deviation value of this measuring point is as follows: Figure 6 As shown.

[0134] In this embodiment, the monitoring results are statistically analyzed: during the start-up process under safe operating conditions, the false alarm rate for bearing temperature monitoring and early warning is 0, demonstrating the accuracy of the invention; for the start-up process with potential fault risks, the early warning rate for bearing temperature monitoring is on average 411 seconds earlier than that relying on traditional threshold methods, demonstrating the sensitivity of the invention, with a fault false alarm rate of 0. It is evident that this invention, by introducing a sliding time window operation, can dynamically capture the changing patterns of bearing temperature over time; combined with vector distance analysis, it quantifies the similarity or difference between data, thereby improving monitoring accuracy and avoiding equipment failures caused by the failure to detect subtle temperature changes in a timely manner; by combining the safe area output by the model with the early warning threshold, it can dynamically adapt to temperature changes under different operating conditions, avoiding the problem of poor adaptability of traditional fixed threshold methods under different operating conditions.

[0135] The embodiments described above are merely preferred embodiments of the present invention and are not intended to limit the invention. Those skilled in the art can make various changes and modifications without departing from the spirit and scope of the invention. Therefore, all technical solutions obtained through equivalent substitution or transformation fall within the protection scope of the present invention.

Claims

1. A method for monitoring bearing temperature during the start-up process of large fluid machinery, characterized in that, The temperature monitoring method is based on sliding time window operation, vector distance analysis, and early warning logic, and includes the following steps: S1. Collect bearing temperature data during the start-up process of fluid machinery to obtain multiple state vectors, and take the state vectors under safe operating conditions to form a model database for the monitoring method; S2. Apply a sliding time window operation to the state vectors in the model database to obtain multiple time window vectors; S3. Calculate the distance between time window vectors, select uniformly distributed time window vectors to form a memory matrix, and obtain the distance matrix of the memory matrix to complete the model construction; S4. During the monitoring period, the state vector corresponding to the bearing temperature during the start-up process of the fluid machinery is subjected to time window operation to obtain the monitoring time window vector, which is used as the input of the model. Calculate the distance between the monitoring time window vector and the time window vector in the memory matrix to obtain the distance vector; obtain the model reconstruction output through vector distance analysis; S5. After obtaining the reconstructed output of multiple continuous monitoring time window vectors, the bearing temperature is monitored during the start-up process of large fluid machinery based on the bearing temperature early warning vector and the monitoring and early warning logic.

2. The monitoring method according to claim 1, characterized in that, Step S1 specifically includes the following steps: S101. During the start-up process of the fluid machinery, bearing temperature data is collected; the bearing temperature data collected each time is used to construct a state vector, as follows: ， in, Indicates the sampling time index. This indicates the number of measuring points for bearing temperature. express The state vector at time t, They represent the first Each bearing temperature measuring point Data at any given time; S102. The state vector under the safe start-up condition of fluid machinery is incorporated into the model database of the monitoring method for model construction.

3. The monitoring method according to claim 1, characterized in that, Step S2 specifically includes the following steps: S201. Apply a time window operation to the state vectors in the model database to obtain the following time window vectors: ， in, This indicates the length of the time window. Represents the time window vector. They represent the first Each bearing temperature measuring point The time window data corresponding to each moment is as follows: ， in, ; S202. Slide the execution of step S201 on the time axis to obtain multiple time window vectors, denoted as... subscript This indicates the number of time window vectors obtained in this step.

4. The monitoring method according to claim 3, characterized in that, Step S3 specifically includes the following steps: S301. Calculate the distance between any two time window vectors, as follows: ， in, , represents the time index of the time window vector. , Represents the two time window vectors involved in the distance calculation. , They represent the first Each bearing temperature measuring point and Time window data corresponding to each moment The Euclidean norm of a vector; S302. By maximizing the minimum distance operation, the time window vectors obtained in step S202 are filtered, and the memory matrix is ​​constructed as follows: ， in, Represents the memory matrix, This indicates the number of time window vectors obtained after filtering. The mapping of the filter satisfies and set The model is ; S303. Construct the distance matrix corresponding to the memory matrix. The distance matrix is The square matrix is ​​as follows: ， Among them, index .

5. The monitoring method according to claim 4, characterized in that, Step S4 specifically includes the following steps: S401. During the startup process of the fluid machinery in the monitoring period, collect bearing temperature data; construct a state vector from the monitored bearing temperature data, as follows: ， in, This indicates the index of the sampling time within the monitoring period. express The state vector at time t, They represent the first Each bearing temperature measuring point Data at any given time; S402. Repeat step S401 during the monitoring period. Based on the obtained multiple state vectors, use a time window operation to obtain a monitoring time window vector as the input to the model, as follows: ， in, Represents the monitoring time window vector. They represent the first Each bearing temperature measuring point The time window data corresponding to each moment is as follows: ， S403, Input of Calculation Model With memory matrix The distances between the vectors within the intermediate time windows are represented by the following distance vectors: ， in, Represents the distance vector. Represents the monitoring time window vector With time window vector The distance is as follows: ， S404. Based on vector distance analysis, the model outputs a monitoring time window vector. The monitoring results are as follows: ， in, The representation model is for The output reconstruction result, scale coefficient Make The sum of the elements is 1.

6. The monitoring method based on claim 5, characterized in that, Step S5 specifically includes the following steps: S501, Results from Model Output extract The reconstructed state vector at time step is as follows: ， in, This indicates the model output in The first state vector reconstructed at time step 1. The first output of the model represents the... Each measuring point is at The first reconstructed value of the time-series data; S502, Time Setting Repeat step S4 to extract. The reconstructed state vectors at time t = ... Moment Reconstructed state vectors ; S503, High Bearing Temperature Warning Vector and low warning vector as follows: ， in Indicates an index; S504, for fluid machinery The first moment Temperature measurement points of each bearing To perform monitoring, set the bearing temperature monitoring deviation value according to the following rules: ， in, , These represent the early warning vectors. , The Each element value; the deviation value indicates the temperature. Deviating from the safe range The degree of deviation is assessed, and warning thresholds are set for the deviation values. Warnings are set according to the degree of deviation, and multi-level warnings are implemented. S505. For the remaining times during the monitoring period, execute steps S501, S502, S503, and S504 of steps S4 and S5 to obtain the monitoring results for the monitoring period, thereby realizing the monitoring of bearing temperature during the start-up process of fluid machinery.

Images