A vibration monitoring method, system and device based on artificial intelligence model

Abstract

This application discloses a vibration monitoring method, system, and device based on an artificial intelligence model, comprising: acquiring first time-series data of a target seismic isolation bearing; obtaining second time-series data of a first seismic isolation bearing based on the association information of the target seismic isolation bearing; obtaining third time-series data of a first device based on the installation information of the target seismic isolation bearing; establishing an initial model; training the initial model to obtain a vibration analysis model; acquiring real-time monitoring data of the target seismic isolation bearing and the first seismic isolation bearing, inputting the real-time monitoring data into the vibration analysis model to obtain predicted operating data; acquiring real-time operating data of the first device in the building where the target seismic isolation bearing is located, and obtaining vibration analysis results based on the real-time operating data and the predicted operating data. This at least solves the problem of a large amount of data assets being wasted in existing systems and the low utilization rate of intelligent bearing monitoring systems.

Description

Technical Field

[0001] The present application relates to the field of production automation technology, and in particular to a vibration monitoring method, system and equipment based on an artificial intelligence model. Background Art

[0002] The seismic isolation bearing of a building is an important component specially designed to reduce the impact of earthquakes on buildings. The core function of the seismic isolation bearing is to "isolate" the direct impact of seismic waves on the building. By adding an isolation layer between the foundation and the superstructure of the building and installing devices such as rubber seismic isolation bearings, the seismic isolation bearing can effectively change the vibration frequency, thereby greatly reducing the seismic effect on the building. Seismic isolation bearings can significantly improve the seismic performance of buildings. Traditional seismic design often focuses on improving the stiffness and strength of the building structure to resist earthquakes. Seismic isolation technology achieves the effect of shock absorption and seismic isolation by extending the natural vibration period of the structure and reducing the transmission of seismic energy to the upper structure. This enables the building to better maintain its integrity and stability when an earthquake occurs, reducing the risk of structural damage and casualties. With the advancement of science and technology, seismic isolation bearings have also developed into various types to meet the needs of different buildings. For example, laminated rubber seismic isolation bearings, high damping rubber seismic isolation bearings, sliding seismic isolation bearings, and lead rubber seismic isolation bearings. These different types of seismic isolation bearings have their own unique performance and characteristics, and can be selected and used in combination according to factors such as the building's structural type, usage function, earthquake intensity and site conditions to achieve the best seismic effect.

[0003] The intelligent bearing monitoring system uses sensor technology, signal acquisition and transmission technology, as well as network technology and software technology to monitor various key technical indicators of the structure under test from a comprehensive perspective combining macro and micro perspectives; record historical and existing data, and analyze future trends in order to assist the owner and government in making decisions, improve the control of changes in the bearing structure, and effectively prevent and curb irreversible trend prevention measures and predictions. In addition to earthquakes, there are many other reasons that can cause building vibrations. The data collected by the intelligent bearing monitoring system is not necessarily directly related to earthquakes, and the existing system will not analyze these data unrelated to earthquakes, resulting in a large amount of data assets being wasted and the utilization rate of the intelligent bearing monitoring system is low. Summary of the invention

[0004] The present invention provides a vibration monitoring method, system and equipment based on an artificial intelligence model, which at least solves the problem that the existing system does not analyze data unrelated to earthquakes, resulting in a large amount of data assets being wasted and the utilization rate of the bearing intelligent monitoring system being low.

[0005] The present invention provides a vibration monitoring method based on an artificial intelligence model, comprising the following steps:

[0006] Acquire first time series data of a target seismic isolation bearing, where the first time series data is configured as historical monitoring data obtained by the target seismic isolation bearing;

[0007] According to the association information of the target seismic isolation support, second time series data of a first seismic isolation support associated with the target seismic isolation support is obtained, wherein the second time series data is configured as historical monitoring data of the first seismic isolation support;

[0008] According to the installation information of the target seismic isolation bearing, third time series data of a first device in the building where the target seismic isolation bearing is located is obtained, wherein the third time series data is configured as historical operation data of the first device in the building where the target seismic isolation bearing is located;

[0009] Establishing an initial model based on the monitoring data of the target seismic isolation support and the monitoring data of the first seismic isolation support as inputs and the operating data of the first equipment in the building where the target seismic isolation support is located as outputs;

[0010] Training the initial model according to the first time series data, the second time series data and the third time series data to obtain a vibration analysis model;

[0011] Acquiring real-time monitoring data of the target seismic isolation bearing and the first seismic isolation bearing, inputting the real-time monitoring data into the vibration analysis model, and obtaining predicted operation data;

[0012] Real-time operation data of a first device in the building where the target seismic isolation bearing is located is obtained, and a vibration analysis result is obtained according to the real-time operation data and the predicted operation data.

[0013] Optionally, obtaining second time series data of a first seismic isolation support associated with the target seismic isolation support according to the associated information of the target seismic isolation support includes:

[0014] According to the target seismic isolation bearing, obtaining a target building where the target seismic isolation bearing is located;

[0015] According to the target building, obtaining at least one first seismic isolation bearing in the target building that is associated with the target seismic isolation bearing;

[0016] Second time series data is obtained based on the historical monitoring data of the first seismic isolation bearing.

[0017] Optionally, obtaining, according to the installation information of the target seismic isolation support, third time series data of a first device in the building where the target seismic isolation support is located includes:

[0018] According to the installation information of the target seismic isolation support, obtaining the target building where the target seismic isolation support is located;

[0019] According to the target building, obtaining at least one first device in the target building and associated with the target seismic isolation bearing;

[0020] The third time series data is obtained according to the historical operation data of the first device.

[0021] Optionally, the establishing of the initial model based on the monitoring data of the target seismic isolation bearing and the monitoring data of the first seismic isolation bearing as input and the operating data of a first device in the building where the target seismic isolation bearing is located as output includes:

[0022] Based on the monitoring data of the target seismic isolation bearing and the monitoring data of the first seismic isolation bearing as input and the operating data of the first device in the building where the target seismic isolation bearing is located as output, an initial model is constructed based on the Transformer architecture, and the initial model includes at least an input layer, an attention layer, and a fully connected layer; and a loss function is selected for the initial model.

[0023] Optionally, the acquiring real-time operating data of a first device in the building where the target seismic isolation bearing is located, and obtaining a vibration analysis result according to the real-time operating data and the predicted operating data, comprises:

[0024] Acquire real-time operation data of a first device in the building where the target seismic isolation bearing is located, and determine the similarity between the real-time operation data and the predicted operation data according to the real-time operation data and the predicted operation data;

[0025] When the similarity is not less than a preset first threshold, a vibration analysis result is obtained according to the real-time operation data.

[0026] Optionally, also include:

[0027] When the similarity is less than a preset first threshold, according to the real-time operation data, based on a vibration prediction model, vibration prediction data of the target seismic isolation bearing corresponding to the real-time operation data is obtained; the vibration prediction model is configured as a prediction model that takes the operation data of a first device in the building where the target seismic isolation bearing is located as input and takes the monitoring data of the target seismic isolation bearing as output;

[0028] Obtaining first difference data according to the vibration prediction data and the real-time monitoring data of the target seismic isolation bearing;

[0029] A vibration analysis result is obtained according to the first difference data.

[0030] Optionally, obtaining a vibration analysis result according to the first difference data includes:

[0031] According to the installation information of the target seismic isolation support, an associated building associated with the building where the target seismic isolation support is located is obtained;

[0032] According to the associated building, second difference data of the associated building is obtained; the second difference data is configured as difference data in the associated building corresponding to the first difference data;

[0033] A vibration analysis result is obtained according to the first difference data and the second difference data.

[0034] In another aspect, a vibration monitoring system based on an artificial intelligence model includes a model management platform and an anomaly detection platform;

[0035] The model management platform is configured to:

[0036] Acquire first time series data of a target seismic isolation bearing, where the first time series data is configured as historical monitoring data obtained by the target seismic isolation bearing;

[0037] According to the association information of the target seismic isolation support, second time series data of a first seismic isolation support associated with the target seismic isolation support is obtained, wherein the second time series data is configured as historical monitoring data of the first seismic isolation support;

[0038] According to the installation information of the target seismic isolation bearing, third time series data of a first device in the building where the target seismic isolation bearing is located is obtained, wherein the third time series data is configured as historical operation data of the first device in the building where the target seismic isolation bearing is located;

[0039] Establishing an initial model based on the monitoring data of the target seismic isolation support and the monitoring data of the first seismic isolation support as inputs and the operating data of the first equipment in the building where the target seismic isolation support is located as outputs;

[0040] Training the initial model according to the first time series data, the second time series data and the third time series data to obtain a vibration analysis model;

[0041] The anomaly detection platform is configured to:

[0042] Acquiring real-time monitoring data of the target seismic isolation bearing and the first seismic isolation bearing, inputting the real-time monitoring data into the vibration analysis model, and obtaining predicted operation data;

[0043] Real-time operation data of a first device in the building where the target seismic isolation bearing is located is obtained, and a vibration analysis result is obtained according to the real-time operation data and the predicted operation data.

[0044] Optionally, the model management platform is further configured to:

[0045] storing a vibration prediction model; the vibration prediction model is configured to take the operation data of the first device in the building where the target seismic isolation bearing is located as an input and the monitoring data of the target seismic isolation bearing as an output;

[0046] The anomaly detection platform is further configured to:

[0047] When the similarity is less than a preset first threshold, obtaining vibration prediction data of the target seismic isolation bearing corresponding to the real-time operation data based on a vibration prediction model according to the real-time operation data;

[0048] Obtaining first difference data according to the vibration prediction data and the real-time monitoring data of the target seismic isolation bearing;

[0049] A vibration analysis result is obtained according to the first difference data.

[0050] On the other hand, a device includes a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement any of the above methods.

[0051] On the other hand, a computer-readable storage medium is provided, wherein a computer program is stored on the computer-readable storage medium, and a processor executes the computer program to implement any of the above methods.

[0052] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0053] The present invention discloses a vibration monitoring method, system and device based on an artificial intelligence model, including: obtaining first time series data of a target seismic isolation bearing, wherein the first time series data is configured as historical monitoring data obtained by the target seismic isolation bearing; obtaining second time series data of a first seismic isolation bearing associated with the target seismic isolation bearing according to associated information of the target seismic isolation bearing, wherein the second time series data is configured as historical monitoring data of the first seismic isolation bearing; obtaining third time series data of a first device in a building where the target seismic isolation bearing is located according to installation information of the target seismic isolation bearing, wherein the third time series data is configured as historical operation data of the first device in the building where the target seismic isolation bearing is located. data; using the monitoring data of the target seismic isolation bearing and the monitoring data of the first seismic isolation bearing as input and the operating data of the first device in the building where the target seismic isolation bearing is located as output, an initial model is established; the initial model is trained according to the first time series data, the second time series data and the third time series data to obtain a vibration analysis model; the real-time monitoring data of the target seismic isolation bearing and the first seismic isolation bearing are obtained, and the real-time monitoring data are input into the vibration analysis model to obtain predicted operating data; the real-time operating data of the first device in the building where the target seismic isolation bearing is located is obtained, and the vibration analysis results are obtained according to the real-time operating data and the predicted operating data. At least the problem that the existing system does not analyze data unrelated to earthquakes, resulting in a large amount of data assets being wasted and the low utilization rate of the bearing intelligent monitoring system is solved. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the specific implementation of the present application or the technical solution in the prior art, the following is a brief introduction to the drawings required for the specific implementation or the prior art description. In all drawings, similar elements or parts are generally identified by similar reference numerals. In the drawings, each element or part is not necessarily drawn according to the actual scale.

[0055] Figure 1 A schematic diagram of the flow of the vibration monitoring method based on the artificial intelligence model in this application;

[0056] Figure 2 This is a schematic diagram of the structure of a computer device in this application.

[0057] Markings in the figure: 101 - processor, 102 - communication bus, 103 - network interface, 104 - user interface, 105 - memory.

[0058] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0059] In order to enable those skilled in the art to better understand the scheme of the present disclosure, the technical scheme in the embodiments of the present disclosure will be clearly and completely described below in conjunction with the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in the field without creative work should fall within the scope of protection of the present disclosure.

[0060] It should be noted that the terms "first", "second", etc. in the specification and claims of the present disclosure and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchangeable where appropriate, so that the embodiments of the present disclosure described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products, or devices.

[0061] Example 1

[0062] like Figure 1 As shown, a vibration monitoring method based on an artificial intelligence model comprises the following steps:

[0063] S1. Obtain first time series data of a target seismic isolation bearing.

[0064] Specifically, the first time series data is configured as historical monitoring data obtained by the target seismic isolation bearing.

[0065] Optionally, the first time series data includes:

[0066] The horizontal displacement time series data of the support is used to characterize the horizontal displacement of the support and then output the horizontal displacement data;

[0067] The bearing vibration time series data is used to characterize the bearing vibration condition and then output the vibration data;

[0068] The time series data of the vertical pressure of the support is used to characterize the vertical pressure of the support and then output the pressure data.

[0069] S2. According to the associated information of the target seismic isolation bearing, obtain second time series data of the first seismic isolation bearing associated with the target seismic isolation bearing.

[0070] Specifically, the second time series data is configured as historical monitoring data of the first seismic isolation bearing.

[0071] Optionally, the second time series data includes:

[0072] The horizontal displacement time series data of the support is used to characterize the horizontal displacement of the support and then output the horizontal displacement data;

[0073] The bearing vibration time series data is used to characterize the bearing vibration condition and then output the vibration data;

[0074] The time series data of the vertical pressure of the support is used to characterize the vertical pressure of the support and then output the pressure data.

[0075] S3. According to the installation information of the target seismic isolation bearing, obtain the third time series data of the first equipment in the building where the target seismic isolation bearing is located.

[0076] Specifically, the third time series data is configured as historical operation data of the first device in the building where the target seismic isolation bearing is located.

[0077] Optionally, the third time series data includes elevator operation time series data, access control time series data, and other data monitored by equipment in the building and used to characterize the activities of people or objects in the building.

[0078] S4. Establish an initial model based on the monitoring data of the target seismic isolation bearing and the monitoring data of the first seismic isolation bearing as input and the operating data of the first equipment in the building where the target seismic isolation bearing is located as output.

[0079] S5. Train the initial model according to the first time series data, the second time series data and the third time series data to obtain a vibration analysis model.

[0080] S6. Acquire real-time monitoring data of the target isolation bearing and the first isolation bearing, input the real-time monitoring data into the vibration analysis model, and obtain predicted operation data.

[0081] S7. Acquire real-time operating data of a first device in the building where the target seismic isolation bearing is located, and obtain a vibration analysis result based on the real-time operating data and the predicted operating data.

[0082] Through the above solution, the monitored vibration data can be associated with the activities in the building, and the cause of the vibration can be further analyzed through the AI ​​model. At least it solves the problem that the existing system does not analyze data unrelated to earthquakes, resulting in a large amount of data assets being wasted and the utilization rate of the bearing intelligent monitoring system is low.

[0083] Example 2

[0084] This embodiment, based on Embodiment 1, provides a vibration monitoring method based on an artificial intelligence model, comprising the following steps:

[0085] S1. Obtain first time series data of a target seismic isolation bearing.

[0086] Specifically, the first time series data is configured as historical monitoring data obtained by the target seismic isolation bearing.

[0087] S2. According to the associated information of the target seismic isolation bearing, obtain second time series data of the first seismic isolation bearing associated with the target seismic isolation bearing.

[0088] Specifically, the second time series data is configured as historical monitoring data of the first seismic isolation bearing.

[0089] Optionally, obtaining second time series data of a first seismic isolation support associated with the target seismic isolation support according to the associated information of the target seismic isolation support includes:

[0090] According to the target seismic isolation bearing, the target building where the target seismic isolation bearing is located is obtained;

[0091] According to the target building, obtaining at least one first seismic isolation bearing associated with the target seismic isolation bearing in the target building;

[0092] The second time series data is obtained according to the historical monitoring data of the first seismic isolation bearing.

[0093] Optionally, according to the target building, the method for obtaining at least one first seismic isolation bearing associated with the target seismic isolation bearing in the target building is to determine at least one first seismic isolation bearing associated with the target seismic isolation bearing in the target building according to architectural design drawings and expert opinions.

[0094] S3. According to the installation information of the target seismic isolation bearing, obtain the third time series data of the first equipment in the building where the target seismic isolation bearing is located.

[0095] Specifically, the third time series data is configured as historical operation data of the first device in the building where the target seismic isolation bearing is located.

[0096] Optionally, obtaining, according to the installation information of the target seismic isolation bearing, third time series data of a first device in the building where the target seismic isolation bearing is located includes:

[0097] According to the installation information of the target seismic isolation bearing, the target building where the target seismic isolation bearing is located is obtained;

[0098] According to the target building, obtaining at least one first device associated with the target seismic isolation bearing in the target building;

[0099] The third time series data is obtained according to the historical operation data of the first device.

[0100] S4. Establish an initial model based on the monitoring data of the target seismic isolation bearing and the monitoring data of the first seismic isolation bearing as input and the operating data of the first equipment in the building where the target seismic isolation bearing is located as output.

[0101] Optionally, an initial model is established based on the monitoring data of the target seismic isolation bearing and the monitoring data of the first seismic isolation bearing as inputs and the operation data of the first equipment in the building where the target seismic isolation bearing is located as outputs, including:

[0102] With the monitoring data of the target isolation bearing and the monitoring data of the first isolation bearing as input and the operating data of the first equipment in the building where the target isolation bearing is located as output, an initial model is constructed based on the Transformer architecture. The initial model includes at least an input layer, an attention layer, and a fully connected layer; and a loss function is selected for the initial model.

[0103] Below is a simple pseudocode to use the Transformer model to predict time series.

[0104] 1. Data preparation;

[0105] Obtain training data;

[0106] X1=first time series data;

[0107] X2=second time series data;

[0108] Y=third time series data

[0109] 2. Data preprocessing;

[0110] def create_dataset(X1, X2, Y, n_steps):

[0111] X, Y_out = [], []

[0112] for i in range(len(Y) - n_steps):

[0113] X.append([X1[i:i+n_steps], X2[i:i+n_steps]])

[0114] Y_out.append(Y[i + n_steps])

[0115] return np.array(X), np.array(Y_out)

[0116] n_steps = 20

[0117] X, Y_out = create_dataset(X1, X2, Y, n_steps)

[0118] scaler = StandardScaler()

[0119] X = scaler.fit_transform(X.reshape(-1, 2)).reshape(-1, n_steps, 2);

[0120] 3. Build the model;

[0121] input_layer = Input(shape=(n_steps, 2))

[0122] attention_output = MultiHeadAttention(num_heads=2, key_dim=2)(input_layer, input_layer)

[0123] x = LayerNormalization(epsilon=1e-6)(input_layer + attention_output)

[0124] x = Dense(64, activation='relu')(x)

[0125] x = Dropout(0.1)(x)

[0126] output_layer = Dense(1)(x)

[0127] model = Model(inputs=input_layer, outputs=output_layer)

[0128] model.compile(optimizer=Adam(learning_rate=0.001), loss='mse');

[0129] 4. Model training

[0130] model.fit(X, Y_out, epochs=50, batch_size=32);

[0131] 5. Prediction

[0132] Y_pred = model.predict(X);

[0133] 6. Result visualization

[0134] import matplotlib.pyplot as plt

[0135] plt.plot(Y_out, label='True Value', color='blue')

[0136] plt.plot(Y_pred, label='Predicted Value', color='red')

[0137] plt.legend()

[0138] plt.show().

[0139] S5. Train the initial model according to the first time series data, the second time series data and the third time series data to obtain a vibration analysis model.

[0140] S6. Acquire real-time monitoring data of the target isolation bearing and the first isolation bearing, input the real-time monitoring data into the vibration analysis model, and obtain predicted operation data.

[0141] S7. Acquire real-time operating data of a first device in the building where the target seismic isolation bearing is located, and obtain a vibration analysis result based on the real-time operating data and the predicted operating data.

[0142] Optionally, obtaining real-time operating data of a first device in a building where the target seismic isolation bearing is located, and obtaining a vibration analysis result according to the real-time operating data and the predicted operating data, including:

[0143] Acquire real-time operation data of a first device in a building where the target seismic isolation bearing is located, and determine the similarity between the real-time operation data and the predicted operation data according to the real-time operation data and the predicted operation data;

[0144] When the similarity is not less than a preset first threshold, a vibration analysis result is obtained according to the real-time operation data.

[0145] Due to the complexity of time series data, similarity judgment needs to consider multiple factors, including time series similarity, shape similarity and change similarity. Optionally, this application uses the following method to perform time series data similarity judgment:

[0146] Minkowski distance judgment: The Minkowski distance model is simple and fast, and is suitable for measuring time series similarity. However, it can only be calculated for time series of equal length and is sensitive to time axis expansion and curvature.

[0147] Dynamic Time Warping Distance Judgment (DTW): DTW is a dynamic programming method that minimizes the distance between two sequences by finding the smallest alignment matching path. It allows time series to shift on the time axis, so the distance between sequences of different lengths can be calculated. DTW is insensitive to time series shifts, can measure the distance between two time series of any length, is insensitive to distortions on the time axis, and has greater applicability and reliability. However, DTW has high computational complexity, is time-consuming, and does not satisfy the triangle inequality.

[0148] Preferably, the present application uses dynamic time warping (DTW) to determine the similarity between real-time operation data and predicted operation data. Since there is an uncontrollable delay between the movements of people or objects in the building and the real-time operation data of the first device, the use of DTW can reduce the deviation.

[0149] Optionally, also include:

[0150] When the similarity is less than a preset first threshold, based on the real-time operation data and the vibration prediction model, vibration prediction data of the target seismic isolation bearing corresponding to the real-time operation data is obtained; the vibration prediction model is configured as a prediction model that takes the operation data of the first device in the building where the target seismic isolation bearing is located as input and takes the monitoring data of the target seismic isolation bearing as output;

[0151] Obtaining first difference data according to the vibration prediction data and the real-time monitoring data of the target seismic isolation bearing;

[0152] A vibration analysis result is obtained based on the first difference data.

[0153] Optionally, a vibration analysis result is obtained according to the first difference data based on a preset indicator system.

[0154] Optionally, according to the first difference data, a method for obtaining a vibration analysis result may be:

[0155] If the first difference data is less than the second threshold value, the vibration analysis result is the vibration caused by external environmental disturbance, such as the passing of a subway, wind blowing, etc.;

[0156] If the first difference data is not less than the second threshold value, the vibration analysis result is vibration caused by an earthquake.

[0157] Optionally, obtaining a vibration analysis result according to the first difference data includes:

[0158] According to the installation information of the target seismic isolation bearing, an associated building associated with the building where the target seismic isolation bearing is located is obtained;

[0159] According to the associated building, second difference data of the associated building is obtained; the second difference data is configured as difference data in the associated building corresponding to the first difference data; that is, the second difference data is difference data between actual vibration data of the associated building through the seismic isolation bearing and vibration data predicted according to actual equipment operation data;

[0160] A vibration analysis result is obtained based on the first difference data and the second difference data.

[0161] Optionally, a vibration analysis result is obtained according to the first difference data and the second difference data based on a preset indicator system.

[0162] Optionally, a method for obtaining a vibration analysis result according to the first difference data and the second difference data may be:

[0163] If the first difference data is less than the second threshold value, and the difference between the first difference data and the second difference data is not greater than the third threshold value, the vibration analysis result is the vibration caused by external environmental disturbance, such as the passing of a subway, wind blowing, etc.;

[0164] If the first difference data is less than the second threshold value, and the difference between the first difference data and the second difference data is greater than the third threshold value, the vibration analysis result is that the target seismic isolation bearing is abnormal;

[0165] If the first difference data is not less than the second threshold value, the vibration analysis result is vibration caused by an earthquake.

[0166] Through the above solution, the influence of internal and external factors of the building is comprehensively considered, a more granular analysis of the causes of vibration is carried out, and the value of vibration data is deeply explored. At least the problem that the existing system does not analyze data unrelated to earthquakes, resulting in a large amount of data assets being wasted and the utilization rate of the bearing intelligent monitoring system is low is solved.

[0167] Optionally, the settings of the first threshold, the second threshold and the third threshold may be obtained through an expert method, or through induction, analysis and calculation of big data.

[0168] Example 3

[0169] A vibration monitoring system based on an artificial intelligence model, including a model management platform and an anomaly detection platform;

[0170] The model management platform is configured to:

[0171] Acquire first time series data of a target seismic isolation bearing, where the first time series data is configured as historical monitoring data obtained by the target seismic isolation bearing;

[0172] According to the association information of the target seismic isolation support, second time series data of the first seismic isolation support associated with the target seismic isolation support is obtained, and the second time series data is configured as historical monitoring data of the first seismic isolation support;

[0173] According to the installation information of the target seismic isolation bearing, third time series data of a first device in the building where the target seismic isolation bearing is located is obtained, and the third time series data is configured as historical operation data of the first device in the building where the target seismic isolation bearing is located;

[0174] An initial model is established based on the monitoring data of the target seismic isolation bearing and the monitoring data of the first seismic isolation bearing as inputs and the operating data of the first equipment in the building where the target seismic isolation bearing is located as outputs;

[0175] The initial model is trained according to the first time series data, the second time series data and the third time series data to obtain a vibration analysis model;

[0176] The anomaly detection platform is configured to:

[0177] Acquire real-time monitoring data of the target seismic isolation bearing and the first seismic isolation bearing, input the real-time monitoring data into the vibration analysis model, and obtain predicted operation data;

[0178] Real-time operation data of a first device in a building where a target seismic isolation bearing is located is obtained, and a vibration analysis result is obtained based on the real-time operation data and the predicted operation data.

[0179] Optionally, the model management platform is also configured to:

[0180] storing a vibration prediction model; the vibration prediction model is configured to take the operation data of the first device in the building where the target seismic isolation bearing is located as an input and the monitoring data of the target seismic isolation bearing as an output;

[0181] The anomaly detection platform is also configured to:

[0182] When the similarity is less than a preset first threshold, obtaining vibration prediction data of a target seismic isolation bearing corresponding to the real-time operation data based on a vibration prediction model according to the real-time operation data;

[0183] Obtaining first difference data according to the vibration prediction data and the real-time monitoring data of the target seismic isolation bearing;

[0184] A vibration analysis result is obtained based on the first difference data.

[0185] Optionally, obtaining a vibration analysis result according to the first difference data includes:

[0186] According to the installation information of the target seismic isolation bearing, an associated building associated with the building where the target seismic isolation bearing is located is obtained;

[0187] According to the associated building, second difference data of the associated building is obtained; the second difference data is configured as difference data in the associated building corresponding to the first difference data;

[0188] A vibration analysis result is obtained based on the first difference data and the second difference data.

[0189] Optionally, obtaining second time series data of a first seismic isolation support associated with the target seismic isolation support according to the associated information of the target seismic isolation support includes:

[0190] According to the target seismic isolation bearing, the target building where the target seismic isolation bearing is located is obtained;

[0191] According to the target building, obtaining at least one first seismic isolation bearing associated with the target seismic isolation bearing in the target building;

[0192] The second time series data is obtained according to the historical monitoring data of the first seismic isolation bearing.

[0193] Optionally, obtaining, according to the installation information of the target seismic isolation bearing, third time series data of a first device in the building where the target seismic isolation bearing is located includes:

[0194] According to the installation information of the target seismic isolation bearing, the target building where the target seismic isolation bearing is located is obtained;

[0195] According to the target building, obtaining at least one first device associated with the target seismic isolation bearing in the target building;

[0196] The third time series data is obtained according to the historical operation data of the first device.

[0197] Optionally, an initial model is established based on the monitoring data of the target seismic isolation bearing and the monitoring data of the first seismic isolation bearing as inputs and the operation data of the first equipment in the building where the target seismic isolation bearing is located as outputs, including:

[0198] With the monitoring data of the target isolation bearing and the monitoring data of the first isolation bearing as input and the operating data of the first equipment in the building where the target isolation bearing is located as output, an initial model is constructed based on the Transformer architecture. The initial model includes at least an input layer, an attention layer, and a fully connected layer; and a loss function is selected for the initial model.

[0199] Optionally, obtaining real-time operating data of a first device in a building where the target seismic isolation bearing is located, and obtaining a vibration analysis result according to the real-time operating data and the predicted operating data, including:

[0200] Acquire real-time operation data of a first device in a building where the target seismic isolation bearing is located, and determine the similarity between the real-time operation data and the predicted operation data according to the real-time operation data and the predicted operation data;

[0201] When the similarity is not less than a preset first threshold, a vibration analysis result is obtained according to the real-time operation data.

[0202] Example 4

[0203] This embodiment provides a device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement any of the above methods.

[0204] Specifically, Figure 2 As shown, Figure 2 This is a schematic diagram of the structure of an electronic device of the hardware operating environment involved in the embodiment of the present application. The electronic device may include: a processor 101, such as a central processing unit (CPU), a communication bus 102, a user interface 104, a network interface 103, and a memory 105. Among them, the communication bus 102 is used to realize the connection and communication between these components. The user interface 104 may include a display (Display), an input unit such as a keyboard (Keyboard), and the user interface 104 may also include a standard wired interface and a wireless interface. The network interface 103 may optionally include a standard wired interface and a wireless interface (such as a wireless fidelity (WIreless-FIdelity, WI-FI) interface). The memory 105 may optionally be a storage device independent of the aforementioned processor 101. The memory 105 may be a high-speed random access memory (RAM) memory, or it may be a stable non-volatile memory (NVM), such as at least one disk storage. The processor 101 may be a general-purpose processor, including a central processing unit, a network processor, etc., or it may be a digital signal processor, an application-specific integrated circuit, a field programmable gate array or other programmable logic device, a discrete gate or transistor logic device, or a discrete hardware component.

[0205] Those skilled in the art will appreciate that Figure 2 The structure shown in the figure does not constitute a limitation on the electronic device, and may include more or less components than shown in the figure, or combine certain components, or arrange the components differently.

[0206] like Figure 2 As shown, the memory 105 as a storage medium may include an operating system, a network communication module, a user interface module, and an application program for implementing a vibration monitoring method based on an artificial intelligence model.

[0207] exist Figure 2In the electronic device shown, the network interface 103 is mainly used for data communication with a network server; the user interface 104 is mainly used for data interaction with a user; the processor 101 and the memory 105 in the present application can be set in the electronic device, and the electronic device calls the application program stored in the memory 105 for implementing a vibration monitoring method based on an artificial intelligence model through the processor 101 to implement the above method.

[0208] Example 5

[0209] This embodiment provides a computer-readable storage medium, on which a computer program is stored, and a processor executes the computer program to implement any of the above methods.

[0210] In some embodiments, the computer readable storage medium may be a memory such as FRAM, ROM, PROM, EPROM, EEPROM, flash memory, magnetic surface memory, optical disk, or CD-ROM; or various devices including one or any combination of the above memories. The computer may be various computing devices including intelligent terminals and servers.

[0211] In the above embodiments of the present disclosure, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0212] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only schematic. For example, the division of units can be a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0213] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed over multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0214] In addition, each functional unit in each embodiment of the present disclosure may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0215] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable non-volatile storage medium. Based on this understanding, the technical solution of the present disclosure is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a non-volatile storage medium, including a number of instructions to enable a device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the various embodiments of the present disclosure. The aforementioned non-volatile storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0216] The above are only preferred embodiments of the present disclosure. It should be pointed out that, for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present disclosure. These improvements and modifications should also be regarded as the protection scope of the present disclosure.

Claims

1. A vibration monitoring method based on an artificial intelligence model, characterized in that: The following steps are involved: Acquire first time series data of a target seismic isolation bearing, where the first time series data is configured as historical monitoring data obtained by the target seismic isolation bearing; According to the association information of the target seismic isolation support, second time series data of a first seismic isolation support associated with the target seismic isolation support is obtained, wherein the second time series data is configured as historical monitoring data of the first seismic isolation support; According to the installation information of the target seismic isolation bearing, third time series data of a first device in the building where the target seismic isolation bearing is located is obtained, wherein the third time series data is configured as historical operation data of the first device in the building where the target seismic isolation bearing is located; Establishing an initial model based on the monitoring data of the target seismic isolation support and the monitoring data of the first seismic isolation support as inputs and the operating data of the first equipment in the building where the target seismic isolation support is located as outputs; Training the initial model according to the first time series data, the second time series data and the third time series data to obtain a vibration analysis model; Acquiring real-time monitoring data of the target seismic isolation bearing and the first seismic isolation bearing, inputting the real-time monitoring data into the vibration analysis model, and obtaining predicted operation data; Acquire real-time operation data of a first device in the building where the target seismic isolation bearing is located, and obtain a vibration analysis result according to the real-time operation data and the predicted operation data; The step of acquiring real-time operation data of a first device in the building where the target seismic isolation bearing is located, and obtaining a vibration analysis result according to the real-time operation data and the predicted operation data, comprises: Acquire real-time operation data of a first device in the building where the target seismic isolation bearing is located, and determine the similarity between the real-time operation data and the predicted operation data according to the real-time operation data and the predicted operation data; When the similarity is not less than a preset first threshold, obtaining a vibration analysis result according to the real-time operation data; When the similarity is less than a preset first threshold, according to the real-time operation data, based on a vibration prediction model, vibration prediction data of the target seismic isolation bearing corresponding to the real-time operation data is obtained; the vibration prediction model is configured as a prediction model that takes the operation data of a first device in the building where the target seismic isolation bearing is located as input and takes the monitoring data of the target seismic isolation bearing as output; Obtaining first difference data according to the vibration prediction data and the real-time monitoring data of the target seismic isolation bearing; Obtaining a vibration analysis result according to the first difference data; The step of obtaining a vibration analysis result according to the first difference data includes: According to the installation information of the target seismic isolation support, an associated building associated with the building where the target seismic isolation support is located is obtained; According to the associated building, second difference data of the associated building is obtained; the second difference data is difference data between actual vibration data of the associated building through the seismic isolation bearing and vibration data predicted according to actual equipment operation data; Obtaining a vibration analysis result according to the first difference data and the second difference data; The method of obtaining the vibration analysis result according to the first difference data and the second difference data is: If the first difference data is less than the second threshold value, and the difference between the first difference data and the second difference data is not greater than the third threshold value, the vibration analysis result is the vibration caused by the external environmental disturbance; If the first difference data is less than the second threshold value, and the difference between the first difference data and the second difference data is greater than the third threshold value, the vibration analysis result is that the target seismic isolation bearing is abnormal; If the first difference data is not less than the second threshold value, the vibration analysis result is vibration caused by an earthquake.

2. A vibration monitoring method based on an artificial intelligence model as claimed in claim 1, characterized in that: The step of obtaining second time series data of a first seismic isolation support associated with the target seismic isolation support according to the associated information of the target seismic isolation support comprises: According to the target seismic isolation bearing, obtaining a target building where the target seismic isolation bearing is located; According to the target building, obtaining at least one first seismic isolation bearing in the target building that is associated with the target seismic isolation bearing; Second time series data is obtained based on the historical monitoring data of the first seismic isolation bearing.

3. A vibration monitoring method based on an artificial intelligence model as claimed in claim 1, characterized in that: The step of obtaining, according to the installation information of the target seismic isolation support, third time series data of a first device in the building where the target seismic isolation support is located comprises: According to the installation information of the target seismic isolation support, obtaining the target building where the target seismic isolation support is located; According to the target building, obtaining at least one first device in the target building and associated with the target seismic isolation bearing; The third time series data is obtained according to the historical operation data of the first device.

4. A vibration monitoring method based on an artificial intelligence model as claimed in claim 1, characterized in that: The initial model is established based on the monitoring data of the target seismic isolation support and the monitoring data of the first seismic isolation support as inputs and the operation data of the first equipment in the building where the target seismic isolation support is located as outputs, including: Based on the monitoring data of the target seismic isolation bearing and the monitoring data of the first seismic isolation bearing as input and the operating data of the first device in the building where the target seismic isolation bearing is located as output, an initial model is constructed based on the Transformer architecture, and the initial model includes at least an input layer, an attention layer, and a fully connected layer; and a loss function is selected for the initial model.

5. A vibration monitoring system based on an artificial intelligence model, characterized in that: Includes model management platform and anomaly detection platform; The model management platform is configured to: Acquire first time series data of a target seismic isolation bearing, where the first time series data is configured as historical monitoring data obtained by the target seismic isolation bearing; According to the association information of the target seismic isolation support, second time series data of a first seismic isolation support associated with the target seismic isolation support is obtained, wherein the second time series data is configured as historical monitoring data of the first seismic isolation support; According to the installation information of the target seismic isolation bearing, third time series data of a first device in the building where the target seismic isolation bearing is located is obtained, wherein the third time series data is configured as historical operation data of the first device in the building where the target seismic isolation bearing is located; Establishing an initial model based on the monitoring data of the target seismic isolation support and the monitoring data of the first seismic isolation support as inputs and the operating data of the first equipment in the building where the target seismic isolation support is located as outputs; Training the initial model according to the first time series data, the second time series data and the third time series data to obtain a vibration analysis model; The anomaly detection platform is configured to: Acquiring real-time monitoring data of the target seismic isolation bearing and the first seismic isolation bearing, inputting the real-time monitoring data into the vibration analysis model, and obtaining predicted operation data; Acquire real-time operation data of a first device in the building where the target seismic isolation bearing is located, and obtain a vibration analysis result according to the real-time operation data and the predicted operation data; The step of acquiring real-time operation data of a first device in the building where the target seismic isolation bearing is located, and obtaining a vibration analysis result according to the real-time operation data and the predicted operation data, comprises: Acquire real-time operation data of a first device in the building where the target seismic isolation bearing is located, and determine the similarity between the real-time operation data and the predicted operation data according to the real-time operation data and the predicted operation data; When the similarity is not less than a preset first threshold, obtaining a vibration analysis result according to the real-time operation data; When the similarity is less than a preset first threshold, according to the real-time operation data, based on a vibration prediction model, vibration prediction data of the target seismic isolation bearing corresponding to the real-time operation data is obtained; the vibration prediction model is configured as a prediction model that takes the operation data of a first device in the building where the target seismic isolation bearing is located as input and takes the monitoring data of the target seismic isolation bearing as output; Obtaining first difference data according to the vibration prediction data and the real-time monitoring data of the target seismic isolation bearing; Obtaining a vibration analysis result according to the first difference data; The step of obtaining a vibration analysis result according to the first difference data includes: According to the installation information of the target seismic isolation support, an associated building associated with the building where the target seismic isolation support is located is obtained; According to the associated building, second difference data of the associated building is obtained; the second difference data is difference data between actual vibration data of the associated building through the seismic isolation bearing and vibration data predicted according to actual equipment operation data; Obtaining a vibration analysis result according to the first difference data and the second difference data; The method of obtaining the vibration analysis result according to the first difference data and the second difference data is: If the first difference data is less than the second threshold value, and the difference between the first difference data and the second difference data is not greater than the third threshold value, the vibration analysis result is the vibration caused by the external environmental disturbance; If the first difference data is less than the second threshold value, and the difference between the first difference data and the second difference data is greater than the third threshold value, the vibration analysis result is that the target seismic isolation bearing is abnormal; If the first difference data is not less than the second threshold value, the vibration analysis result is vibration caused by an earthquake.

6. An electronic device, characterized in that: The electronic device comprises a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method according to any one of claims 1 to 4.

Images