Building structure assembly operation management system and method

Abstract

The present application relates to the field of intelligent management, and specifically discloses a building structure assembly operation management system and method, which collects the performance of building components in real time through sensors installed in various parts of the building to obtain the time series of the performance of building components, wherein the performance of building components includes temperature and humidity, energy consumption, and vibration, and obtains data on the use of building components, wherein the data on the use of building components includes the frequency of use and the mode of use, and uses artificial intelligence technology to perform time series feature analysis and semantic understanding on the data on the performance of building components and the use of building components, thereby generating a judgment result on whether maintenance is required. In this way, potential failures and performance degradation can be predicted, so that measures can be taken in advance to reduce unexpected downtime and maintenance costs, thereby improving the operating efficiency and safety of the building and improving the overall performance of the building.

Description

Technical Field

[0001] The present application relates to the field of intelligent management, and more specifically, to a system and method for the operation and management of assembled building structures. Background Art

[0002] Prefabricated building structure operation management refers to the full life cycle management of buildings constructed using prefabricated building technology, which includes the design, construction, operation and maintenance of buildings, and the final demolition and recycling. Prefabricated buildings refer to the main parts of buildings, such as walls, columns, beams, floor slabs, roofs, etc., which are prefabricated in factories and then transported to the construction site for assembly. This construction method has many advantages, such as shortening construction period, facilitating construction, improving building quality, protecting the environment and controlling costs.

[0003] The operation and maintenance process is a key component in the building structure assembly operation and management system. It is mainly responsible for the daily maintenance and long-term care of the building during operation.

[0004] However, traditional building maintenance usually relies on regular manual inspections to identify problems, which is not only inefficient but also susceptible to human error. Secondly, due to the lack of real-time monitoring, traditional maintenance often takes action only after a problem occurs, which is slow to respond and may cause the problem to worsen.

[0005] Therefore, an optimized building structure assembly operation and management system is expected. Summary of the invention

[0006] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides a building structure assembly operation management system and method, which collects information about the performance of building components in real time through sensors installed in various parts of the building to obtain a time series of the performance of building components, wherein the performance of the building components includes temperature and humidity, energy consumption, and vibration, and obtains data on the use of building components, wherein the data on the use of building components includes usage frequency and usage mode, and uses artificial intelligence technology to perform time series feature analysis and semantic understanding on the data on the performance of the building components and the use of the building components, thereby generating a judgment result on whether maintenance is required. In this way, potential failures and performance degradation can be predicted, so that measures can be taken in advance to reduce unexpected downtime and maintenance costs, thereby improving the operating efficiency and safety of the building and improving the overall performance of the building.

[0007] According to one aspect of the present application, a building structure assembly operation management system is provided, which includes:

[0008] A building component performance collection module, which is used to collect the performance of building components in real time through sensors installed in various parts of the building to obtain a time series of the performance of building components, wherein the performance of building components includes temperature and humidity, energy consumption, and vibration;

[0009] A building component usage acquisition module, used to acquire data on the usage of building components, wherein the data on the usage of building components includes usage frequency and usage mode;

[0010] A component performance arrangement module, used for arranging the time series of the building component performance into a sequence of building component performance time series input vectors according to the time dimension and the sample dimension;

[0011] A component performance feature extraction module, used to obtain a building component performance time series semantic feature vector based on the sequence of the building component performance time series input vector;

[0012] A data semantic extraction module, used for performing building component usage data semantic extraction on the data of the building component usage to obtain a building component usage data semantic feature vector;

[0013] A building component operation data feature fusion module, used for fusing the building component performance time series semantic feature vector and the building component usage data semantic feature vector to obtain a building component operation data fusion feature vector;

[0014] The judgment result generating module is used to obtain the judgment result based on the building component operation data fusion feature vector.

[0015] According to another aspect of the present application, a method for operation and management of an assembled building structure is provided, comprising:

[0016] The performance of building components is collected in real time by sensors installed in various places of the building to obtain a time series of the performance of the building components, wherein the performance of the building components includes temperature, humidity, energy consumption, and vibration;

[0017] Acquiring data on the use of building components, wherein the data on the use of building components includes a use frequency and a use pattern;

[0018] Arranging the time series of the building component performance into a sequence of building component performance time series input vectors according to the time dimension and the sample dimension;

[0019] Based on the sequence of the building component performance time series input vector, obtaining a building component performance time series semantic feature vector;

[0020] Performing building component usage data semantic extraction on the data of the building component usage to obtain a building component usage data semantic feature vector;

[0021] Fusing the building component performance time series semantic feature vector and the building component usage data semantic feature vector to obtain a building component operation data fusion feature vector;

[0022] Based on the building component operation data, the feature vector is fused to obtain a judgment result.

[0023] Compared with the prior art, the present application provides a building structure assembly operation management system and method, which collects the performance of building components in real time through sensors installed in various parts of the building to obtain the time series of the performance of building components, wherein the performance of building components includes temperature and humidity, energy consumption, and vibration, and obtains data on the use of building components, wherein the data on the use of building components includes the frequency of use and the mode of use, and uses artificial intelligence technology to perform time series feature analysis and semantic understanding on the data on the performance of building components and the use of building components, thereby generating a judgment result on whether maintenance is required. In this way, potential failures and performance degradation can be predicted, so that measures can be taken in advance to reduce unexpected downtime and maintenance costs, thereby improving the operating efficiency and safety of the building and improving the overall performance of the building. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying drawings are used to provide a further understanding of the embodiments of the present application and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0025] Figure 1 It is a block diagram of the building structure assembly operation management system according to an embodiment of the present application.

[0026] Figure 2 It is a schematic diagram of the architecture of the building structure assembly operation management system according to an embodiment of the present application.

[0027] Figure 3 It is a block diagram of a component performance feature extraction module in a building structure assembly operation management system according to an embodiment of the present application.

[0028] Figure 4 It is a block diagram of a judgment result generation module in the building structure assembly operation management system according to an embodiment of the present application.

[0029] Figure 5 It is a flow chart of the method for prefabricated operation and management of building structures according to an embodiment of the present application. DETAILED DESCRIPTION

[0030] The embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although certain embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be construed as being limited to the embodiments described herein, but rather these embodiments are provided for a more thorough and complete understanding of the present disclosure. It should be understood that the drawings and embodiments of the present disclosure are only for exemplary purposes and are not intended to limit the scope of protection of the present disclosure.

[0031] It should be understood that the various steps described in the method embodiments of the present disclosure may be performed in different orders and / or in parallel. In addition, the method embodiments may include additional steps and / or omit the steps shown. The scope of the present disclosure is not limited in this respect.

[0032] It should be noted that the terms "first\second\third" involved in the embodiments of the present application are only used to distinguish similar objects, and do not represent a specific order for the objects. It is understandable that the specific order or sequence of "first\second\third" can be interchanged where permitted. It should be understood that the objects distinguished by "first\second\third" can be interchanged where appropriate, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein.

[0033] As shown in the present disclosure and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0034] Various exemplary embodiments, features and aspects of the present disclosure will be described in detail below with reference to the accompanying drawings. The same reference numerals in the accompanying drawings represent elements with the same or similar functions. Although various aspects of the embodiments are shown in the accompanying drawings, the drawings are not necessarily drawn to scale unless otherwise specified.

[0035] Prefabricated construction is a modern industrialized construction production method that transfers a large number of on-site operations in traditional construction to a factory environment. In the factory, building components and accessories (such as floor slabs, wall panels, stairs, balconies, etc.) are prefabricated, then transported to the construction site and assembled and installed using reliable connection methods to form a complete building. This construction method has many advantages, such as shortening the construction period, facilitating construction, improving building quality, protecting the environment and controlling costs.

[0036] The operation and management of prefabricated building structures refers to the full life cycle management of buildings constructed using prefabricated building technology, which includes the design, construction, operation and maintenance of buildings, and the final demolition and recycling. The operation and maintenance process is a key component of the prefabricated building structure operation and management system. It is mainly responsible for the daily maintenance and long-term care of the building during operation. Through regular inspection and maintenance, cracks, deformations or other damages that may occur in the building structure can be discovered and repaired in time, thereby ensuring the safety of the building, extending the service life of the building, and reducing early damage or functional degradation caused by improper maintenance.

[0037] However, traditional building maintenance usually relies on regular manual inspections to identify problems, which is not only inefficient but also susceptible to human error. Secondly, due to the lack of real-time monitoring, traditional maintenance often takes action only after a problem occurs, which is slow to respond and may cause the problem to worsen.

[0038] Therefore, an optimized building structure assembly operation management system is desired, which collects the performance of building components in real time through sensors installed in various parts of the building to obtain the time series of the performance of building components, wherein the performance of building components includes temperature and humidity, energy consumption, and vibration, and obtains the data of the use of building components, wherein the data of the use of building components includes the frequency of use and the mode of use, and uses artificial intelligence technology to perform time series feature analysis and semantic understanding on the data of the performance of building components and the use of building components, thereby generating a judgment result on whether maintenance is required. In this way, potential failures and performance degradation can be predicted, so that measures can be taken in advance to reduce unexpected downtime and maintenance costs, thereby improving the operation efficiency and safety of the building and improving the overall performance of the building.

[0039] Figure 1 It is a block diagram of the building structure assembly operation management system according to an embodiment of the present application. Figure 2 FIG. 1 is a schematic diagram of the architecture of the building structure assembly operation management system according to an embodiment of the present application. Figure 1 and Figure 2As shown, according to the embodiment of the present application, the building structure assembly operation management system 100 includes: a building component performance collection module 110, which is used to collect the performance of building components in real time through sensors installed in various parts of the building to obtain a time series of the performance of building components, wherein the building component performance includes temperature and humidity, energy consumption, and vibration; a building component usage acquisition module 120, which is used to obtain data on the usage of building components, wherein the data on the usage of building components includes usage frequency and usage mode; a component performance arrangement module 130, which is used to arrange the time series of the performance of building components into a sequence of building component performance time series input vectors according to the time dimension and the sample dimension; The performance feature extraction module 140 is used to obtain a building component performance time series semantic feature vector based on the sequence of the building component performance time series input vector; the data semantic extraction module 150 is used to perform building component usage data semantic extraction on the data of the building component usage to obtain a building component usage data semantic feature vector; the building component operation data feature fusion module 160 is used to perform feature fusion on the building component performance time series semantic feature vector and the building component usage data semantic feature vector to obtain a building component operation data fusion feature vector; and the judgment result generation module 170 is used to obtain a judgment result based on the building component operation data fusion feature vector.

[0040] In the embodiment of the present application, the building component performance collection module 110 is used to collect the performance of building components in real time through sensors installed in various parts of the building to obtain a time series of the performance of building components, wherein the performance of building components includes temperature and humidity, energy consumption, and vibration. It should be understood that considering the temperature and humidity, the energy consumption, and the vibration are important factors in the operation and maintenance of building components. In detail, the temperature and humidity reflect the thermal comfort and humidity of the internal and external environment of the building, and can reveal the insulation performance and possible heat loss problems of the building. The energy consumption reflects the energy consumption of the building during use, including electricity, water, and heat energy. The vibration reflects the response of the building structure under dynamic loads (such as wind, earthquake, traffic, etc.). The vibration data can be used to evaluate the safety and seismic performance of the building structure. Based on this, in order to ensure the safety of the building structure so that possible structural problems can be discovered and handled in a timely manner, in the technical solution of the present application, the performance of building components is collected in real time through sensors installed in various parts of the building to obtain a time series of the performance of building components, wherein the performance of building components includes temperature and humidity, energy consumption, and vibration.

[0041] In the embodiment of the present application, the building component usage acquisition module 120 is used to acquire data on the usage of building components, wherein the data on the usage of building components includes usage frequency and usage pattern. Accordingly, it is considered that the usage frequency reflects the frequency of use of building components in daily use. For example, the usage frequency of doors, elevators, etc. can reveal the busy areas and peak usage periods of the building. The usage pattern describes how the building components are used. Based on this, in order to deeply understand and analyze the actual performance and user behavior of the building during use, generally subsequent operation and maintenance judgments are made, in the technical solution of the present application, data on the usage of building components are acquired, wherein the data on the usage of building components includes usage frequency and usage pattern.

[0042] In the embodiment of the present application, the component performance arrangement module 130 is used to arrange the time series of the building component performance according to the time dimension and the sample dimension into a sequence of the building component performance time series input vector. It should be understood that considering that the building component performance including temperature and humidity, energy consumption, and vibration is constantly changing with the fluctuation of time, that is, the building component performance has certain time series characteristics on the time scale, and the temperature and humidity, the energy consumption, and the vibration have certain correlation and mutual influence on the time dimension. Based on this, in order to retain the characteristic information of the building component performance in the time dimension, and in order to more accurately analyze the time series correlation between each building performance, in the technical solution of the present application, the time series of the building component performance is arranged according to the time dimension and the sample dimension into a sequence of the building component performance time series input vector, so that the time series characteristics of the building component performance, such as periodic changes and fluctuations, etc., can be better analyzed, providing support and basis for the judgment of subsequent building component maintenance.

[0043] In the embodiment of the present application, the component performance feature extraction module 140 is used to obtain a building component performance time series semantic feature vector based on the sequence of the building component performance time series input vector. Figure 3 is a block diagram of a component performance feature extraction module in a building structure assembly operation management system according to an embodiment of the present application. Specifically, in the embodiment of the present application, Figure 3 As shown, the component performance feature extraction module 140 includes: a component performance time series feature extraction unit 141, used to perform component performance time series feature extraction on the sequence of the building component performance time series input vectors to obtain a sequence of building component performance time series feature vectors; and a component performance time series semantic extraction unit 142, used to perform data semantic extraction on the sequence of the building component performance time series feature vectors to obtain the building component performance time series semantic feature vector.

[0044] Specifically, the component performance time series feature extraction unit 141 is used to extract component performance time series features from the sequence of the building component performance time series input vectors to obtain a sequence of building component performance time series feature vectors. Specifically, in the embodiment of the present application, the component performance time series feature extraction unit is used to: input the sequence of the building component performance time series input vectors into a component performance time series feature extraction module based on a one-dimensional convolution layer to obtain a sequence of the building component performance time series feature vectors. Accordingly, considering that each building component performance time series input vector in the sequence of the building component performance time series input vectors has local construction performance time series feature information, and considering that the one-dimensional convolution layer is good at capturing local time series patterns and trends in sequence data, this is very important for understanding the changes in component performance. Therefore, in order to better understand the feature information of each building component performance time series input vector in the sequence of the building component performance time series input vectors about the building construction performance at local time, in the technical solution of the present application, the sequence of the building component performance time series input vectors is input into a component performance time series feature extraction module based on a one-dimensional convolution layer to obtain a sequence of the building component performance time series feature vectors.

[0045] Specifically, the component performance time series semantic extraction unit 142 is used to perform data semantic extraction on the sequence of the building component performance time series feature vector to obtain the building component performance time series semantic feature vector. Specifically, in the embodiment of the present application, the component performance time series semantic extraction unit is used to: input the sequence of the building component performance time series feature vector into the data semantic extraction module based on the bidirectional LSTM model to obtain the building component performance time series semantic feature vector. It should be understood that considering that the sequence of the building component performance time series feature vector reflects the characteristic information of each building energy in the local time series, and there is also a time series association between the contexts of the building performance between each building component performance time series feature vector in the sequence of the building component performance time series feature vector. And considering that the bidirectional LSTM model is good at extracting deep time series semantic features from sequence data. Specifically, the bidirectional LSTM is an extension of LSTM, which processes sequence data through two LSTM layers in opposite directions, one processing forward (future to past) and the other processing reverse (past to future). Therefore, in order to capture and mine the deep semantic feature information between each building component performance time series feature vector in the sequence of the building component performance time series feature vector so as to better characterize the performance characteristics of the building component, in the technical solution of the present application, the sequence of the building component performance time series feature vector is input into a data semantic extraction module based on a bidirectional LSTM model to obtain the building component performance time series semantic feature vector.

[0046] In particular, in an achievable embodiment of the present application, data semantic extraction is performed on the sequence of the building component performance time series feature vectors to obtain the building component performance time series semantic feature vectors, which can be achieved in the following manner. First, the similarity between the sequences of the building component performance time series feature vectors is calculated, and a clustering algorithm or a similarity measurement method, such as cosine similarity, can be used. And based on the results of the similarity analysis, similar building component performance time series feature vectors are identified and extracted, and these feature vectors may represent similar performance patterns or behaviors. Then, the extracted building component performance time series feature vectors with semantic information are fused, and weighted averaging or other integration methods can be used. Next, the fused feature vectors are combined into a building component performance time series semantic feature vector, which captures the semantic information of the building component performance data. Through these steps, data semantic extraction can be performed on the sequence of building component performance time series feature vectors, thereby obtaining a building component performance time series semantic feature vector with more semantic information.

[0047] In an embodiment of the present application, the data semantic extraction module 150 is used to perform semantic extraction of the building component usage data on the data of the building component usage to obtain a semantic feature vector of the building component usage data. Specifically, in an embodiment of the present application, the data semantic extraction module is used to: input the data of the building component usage into a building component usage data semantic extractor based on the Bert model to obtain a semantic feature vector of the building component usage data. Accordingly, it is considered that the data of the building component usage reflects the usage frequency and usage pattern of the building component. There is semantic feature association information between the contexts between these usage data, and it is also considered that the BERT model can capture the bidirectional context information of the vocabulary through its Transformer architecture, which helps to more accurately understand the semantics behind the component usage data. Therefore, in the technical solution of the present application, the data on the usage of the building components is input into a building component usage data semantic extractor based on the Bert model to obtain a semantic feature vector of the building component usage data. That is to say, the semantic extractor for building component usage data based on the Bert model performs semantic analysis and semantic understanding on the data on the usage of the building components, so as to generate a rich, high-dimensional semantic feature vector of the building component usage data. The semantic feature vector of the building component usage data contains detailed information on the component usage, which is helpful for subsequent more detailed construction information analysis.

[0048] In the embodiment of the present application, the building component operation data feature fusion module 160 is used to fuse the building component performance time series semantic feature vector and the building component usage data semantic feature vector to obtain the building component operation data fusion feature vector. It should be understood that considering that the building component performance time series semantic feature vector contains semantic information extracted from the time series data of the building component performance, such as the energy consumption pattern, vibration characteristics, temperature and humidity changes of the component, etc., these features reflect the dynamic behavior and performance changes of the component over time. The building component usage data semantic feature vector respectively represents the semantic information extracted from the usage data of the building component, such as usage frequency, usage mode, user behavior, etc. These features reflect how the component is used, as well as the user's usage habits and preferences. Therefore, in order to provide a more comprehensive view of the performance and usage of the building component, in the technical solution of the present application, the building component performance time series semantic feature vector and the building component usage data semantic feature vector are feature fused to obtain the building component operation data fusion feature vector. It should be understandable that the building component operation data fusion feature vector can provide richer semantic information for operation and maintenance decisions, help formulate more effective maintenance and optimization strategies, and provide deeper insights and more efficient solutions for building operation and maintenance.

[0049] In the embodiment of the present application, the judgment result generating module 170 is used to obtain a judgment result based on the building component operation data fused with the feature vector. Figure 4 : is a block diagram of a judgment result generation module in a building structure assembly operation management system according to an embodiment of the present application. Specifically, in the embodiment of the present application, Figure 4 As shown, the judgment result generating module 170 includes: a feature optimization unit 171, used for optimizing the building component operation data fusion feature vector to obtain an optimized building component operation data fusion feature vector; and a maintenance judgment unit 172, used for inputting the optimized building component operation data fusion feature vector into a classifier-based maintenance judgement device to obtain a judgment result, and the judgment result is used to indicate whether maintenance is required.

[0050] Specifically, the feature optimization unit 171 is used to optimize the building component operation data fusion feature vector to obtain an optimized building component operation data fusion feature vector. Specifically, in the embodiment of the present application, the feature optimization unit includes: a correction feature calculation subunit, which is used to perform label dependency recognition fusion based on feature representation on the building component performance time series semantic feature vector and the building component use data semantic feature vector to obtain a correction feature vector; and a feature weighting subunit, which is used to calculate the position point multiplication between the correction feature vector and the building component operation data fusion feature vector to obtain the optimized building component operation data fusion feature vector. In particular, in the technical solution of the present application, on the one hand, it is considered that the building component performance time series semantic feature vector focuses on reflecting the performance changes of building components, such as the changes over time in temperature, humidity, energy consumption and vibration. The building component use data semantic feature vector focuses on the use of building components, such as the frequency and mode of use. These two types of information provide two key perspectives for building maintenance. Position complementary information refers to the unique information provided by two different types of data. Performance time series data may focus more on the physical state and environmental impact of components, while usage data provides information about component usage patterns and usage intensity. By utilizing the positional complementary information of different feature sets, the system can more comprehensively evaluate the actual condition of building components, thereby improving the accuracy of maintenance judgments. On the other hand, considering that in actual building maintenance data, most component status data may indicate that maintenance is not required, while there are fewer component status data that require maintenance, resulting in uneven label distribution. This unevenness may cause the model to tend to predict the majority class (no maintenance required) while ignoring the minority class (maintenance required). Therefore, in the technical solution of the present application, the building component performance time series semantic feature vector and the building component usage data semantic feature vector are subjected to feature representation-based label dependency recognition fusion.

[0051] More specifically, in an embodiment of the present application, the correction feature calculation subunit is used to: calculate the position-based mean vector between the building component performance time series semantic feature vector and the building component usage data semantic feature vector; calculate the mean and variance of a feature set composed of all eigenvalues ​​of the position-based mean vector; use the mean of the eigenvalues ​​of the predetermined positions of the building component performance time series semantic feature vector and the building component usage data semantic feature vector as the exponent of the natural constant to calculate an exponential function value with the natural constant as the base to obtain a first exponential function value; use the opposite number of the variance of the feature set as the exponent of the natural constant to calculate an exponential function value with the natural constant as the base and then subtract one to obtain an exponential adjustment difference; divide the first exponential function value by the exponential adjustment difference and then subtract the mean of the feature set, and activate the calculated difference through a ReLU function to obtain a first activation value; take the absolute value of the first activation value and then activate it through a Se lu function to obtain a second activation value; and multiply the second activation value by the first exponential function value to obtain the eigenvalue of the predetermined position of the correction feature vector.

[0052] Preferably, in an embodiment of the present application, the correction feature calculation subunit is used to: perform label dependency recognition fusion based on feature representation on the building component performance time series semantic feature vector and the building component usage data semantic feature vector using the following fusion formula to obtain the correction feature vector; wherein the fusion formula is:

[0053]

[0054] in, represents the eigenvalue of the i-th position of the temporal semantic feature vector of the building component performance, represents the eigenvalue of the ith position of the semantic feature vector of the building component usage data, μ and σ are the mean and variance of the feature set consisting of all eigenvalues ​​of the position mean vector between the building component performance time series semantic feature vector and the building component usage data semantic feature vector, ReLU represents the linear rectification function, Selu represents the Selu activation function, and v i ' represents the eigenvalue of the i-th position of the corrected eigenvector.

[0055] In particular, here, the building component performance time series semantic feature vector and the building component usage data semantic feature vector are subjected to label dependency recognition fusion based on feature representation. By stacking different feature vectors and considering their distribution in the feature space, the model can better understand and process unseen data, thereby enhancing the generalization ability of the model. At the same time, the dependency of label positions enables the model to more accurately identify and classify data points, especially in cases with obvious boundaries or groups, thereby improving the classification accuracy. Moreover, label dependency recognition fusion based on feature representation can optimize the feature representation of the data, making similar data points closer in the feature space and different data points more dispersed, thereby helping the decision-making of the classifier.

[0056] Specifically, the maintenance judgment unit 172 is used to input the optimized building component operation data fusion feature vector into the maintenance judgement based on the classifier to obtain a judgment result, and the judgment result is used to indicate whether maintenance is required. That is, the optimized building component operation data fusion feature vector is used for classification processing to generate a judgment result of whether maintenance is required. In this way, potential failures and performance degradation can be predicted, so that measures can be taken in advance to reduce unexpected downtime and maintenance costs, thereby improving the operation efficiency and safety of the building and improving the overall performance of the building.

[0057] In summary, the building structure assembly operation management system 100 based on the embodiment of the present application is explained, which collects the performance of building components in real time through sensors installed in various parts of the building to obtain the time series of the performance of building components, wherein the performance of building components includes temperature and humidity, energy consumption, and vibration, and obtains data on the use of building components, wherein the data on the use of building components includes the frequency of use and the mode of use, and uses artificial intelligence technology to perform time series feature analysis and semantic understanding on the data on the performance of building components and the use of building components, thereby generating a judgment result on whether maintenance is required. In this way, potential failures and performance degradation can be predicted, so that measures can be taken in advance to reduce unexpected downtime and maintenance costs, thereby improving the operating efficiency and safety of the building and improving the overall performance of the building.

[0058] Figure 5 Flow chart of the method for building structure assembly operation management according to an embodiment of the present application. Figure 5As shown, according to the embodiment of the present application, the method for prefabricated operation and management of building structures includes: S110, collecting information about building component performance in real time through sensors installed at various locations of the building to obtain a time series of building component performance, wherein the building component performance includes temperature and humidity, energy consumption, and vibration; S120, acquiring data on building component usage, wherein the building component usage data includes usage frequency and usage mode; S130, arranging the time series of building component performance into a sequence of building component performance time series input vectors according to the time dimension and the sample dimension; S140, obtaining a building component performance time series semantic feature vector based on the sequence of the building component performance time series input vector; S150, performing building component usage data semantic extraction on the building component usage data to obtain a building component usage data semantic feature vector; S160, performing feature fusion on the building component performance time series semantic feature vector and the building component usage data semantic feature vector to obtain a building component operation data fusion feature vector; and, S170, obtaining a judgment result based on the building component operation data fusion feature vector.

[0059] Here, those skilled in the art can understand that the specific operations of each step in the above-mentioned building structure assembly operation management method have been referred to above. Figures 1 to 4 The invention has been introduced in detail in the description of the building structure prefabricated operation management system, and therefore, its repeated description will be omitted.

[0060] According to an exemplary implementation of the present disclosure, a computer-readable storage medium is provided, on which computer-executable instructions are stored, wherein the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is also provided, the computer program product is tangibly stored on a non-transitory computer-readable medium and includes computer-executable instructions, and the computer-executable instructions are executed by a processor to implement the method described above. According to an exemplary implementation of the present disclosure, a computer program product is provided, on which a computer program is stored, and when the program is executed by a processor, the method described above is implemented.

[0061] Various aspects of the present disclosure are described herein with reference to flowcharts and / or block diagrams of methods, devices, equipment, and computer program products implemented according to the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of boxes in the flowchart and / or block diagram can be implemented by computer-readable program instructions.

[0062] In addition, although the operations are depicted in a particular order, this should be understood as requiring that such operations be performed in the particular order shown or in a sequential order, or requiring that all illustrated operations be performed to achieve the desired results. In certain environments, multitasking and parallel processing may be advantageous. Similarly, although several specific implementation details are included in the above discussion, these should not be interpreted as limiting the scope of the present disclosure. Certain features described in the context of separate embodiments may also be implemented in a single implementation in combination. Conversely, various features described in the context of a single implementation may also be implemented in multiple implementations individually or in any suitable sub-combination.

[0063] Although the subject matter has been described in language specific to structural features and / or methodological logical actions, it should be understood that the subject matter defined in the appended claims is not necessarily limited to the specific features or actions described above. Instead, the specific features and actions described above are merely example forms of implementing the claims.

Claims

1. A building structure assembly operation management system, characterized in that: include: A building component performance collection module, which is used to collect the performance of building components in real time through sensors installed in various parts of the building to obtain a time series of the performance of building components, wherein the performance of building components includes temperature and humidity, energy consumption, and vibration; A building component usage acquisition module, used to acquire data on the usage of building components, wherein the data on the usage of building components includes usage frequency and usage mode; A component performance arrangement module, used for arranging the time series of the building component performance into a sequence of building component performance time series input vectors according to the time dimension and the sample dimension; A component performance feature extraction module, used to obtain a building component performance time series semantic feature vector based on the sequence of the building component performance time series input vector; A data semantic extraction module, used for performing building component usage data semantic extraction on the data of the building component usage to obtain a building component usage data semantic feature vector; A building component operation data feature fusion module, used for fusing the building component performance time series semantic feature vector and the building component usage data semantic feature vector to obtain a building component operation data fusion feature vector; A judgment result generating module, used for fusing the feature vector based on the building component operation data to obtain a judgment result; Wherein, the judgment result generating module includes: A feature optimization unit, used for optimizing the building component operation data fusion feature vector to obtain an optimized building component operation data fusion feature vector; A maintenance judgment unit, used for inputting the optimized building component operation data fusion feature vector into a maintenance judge based on a classifier to obtain a judgment result, wherein the judgment result is used to indicate whether maintenance is required; Wherein, the feature optimization unit comprises: A correction feature calculation subunit, used for performing label dependency recognition fusion based on feature representation on the building component performance time series semantic feature vector and the building component usage data semantic feature vector to obtain a correction feature vector; A feature weighting subunit, for calculating a position point multiplication between the correction feature vector and the building component operation data fusion feature vector to obtain the optimized building component operation data fusion feature vector; Wherein, the correction feature calculation subunit is used for: Calculating a position-based mean vector between the building component performance time series semantic feature vector and the building component usage data semantic feature vector; Calculate the mean and variance of a feature set consisting of all eigenvalues ​​of the position-wise mean vector; Using the mean of the characteristic values ​​of the building component performance time series semantic characteristic vector and the predetermined position of the building component usage data semantic characteristic vector as the exponent of the natural constant, an exponential function value with the natural constant as the base is calculated to obtain a first exponential function value; Using the inverse of the variance of the feature set as the exponent of the natural constant, calculating an exponential function value with the natural constant as the base and then subtracting one to obtain an exponential adjustment difference; Dividing the first exponential function value by the exponential adjustment difference value and then subtracting the mean value of the feature set, and activating the calculated difference value through a ReLU function to obtain a first activation value; Taking the absolute value of the first activation value and then activating it through the Selu function to obtain a second activation value; The second activation value is multiplied by the first exponential function value to obtain a feature value at a predetermined position of the corrected feature vector.

2. The building structure assembly operation management system according to claim 1, characterized in that: The component performance feature extraction module comprises: A component performance time series feature extraction unit, used for extracting component performance time series features from the sequence of building component performance time series input vectors to obtain a sequence of building component performance time series feature vectors; The component performance time series semantic extraction unit is used to perform data semantic extraction on the sequence of the building component performance time series feature vector to obtain the building component performance time series semantic feature vector.

3. The building structure assembly operation management system according to claim 2, characterized in that: The component performance time series feature extraction unit is used to: The sequence of the building component performance time series input vectors is input into a component performance time series feature extraction module based on a one-dimensional convolutional layer to obtain a sequence of the building component performance time series feature vectors.

4. The building structure assembly operation management system according to claim 3, characterized in that: The component performance temporal semantic extraction unit is used to: The sequence of the building component performance time series feature vector is input into a data semantic extraction module based on a bidirectional LSTM model to obtain the building component performance time series semantic feature vector.

5. The building structure assembly operation management system according to claim 4, characterized in that: The data semantic extraction module is used to: The data of the building component usage is input into a building component usage data semantic extractor based on the Bert model to obtain the building component usage data semantic feature vector.

6. A method for operation and management of assembled building structures, using the assembled building structure operation and management system according to claim 1, characterized in that: include: The performance of building components is collected in real time by sensors installed in various places of the building to obtain a time series of the performance of the building components, wherein the performance of the building components includes temperature, humidity, energy consumption, and vibration; Acquiring data on the use of building components, wherein the data on the use of building components includes a use frequency and a use pattern; Arranging the time series of the building component performance into a sequence of building component performance time series input vectors according to the time dimension and the sample dimension; Based on the sequence of the building component performance time series input vector, obtaining a building component performance time series semantic feature vector; Performing building component usage data semantic extraction on the data of the building component usage to obtain a building component usage data semantic feature vector; Performing feature fusion on the building component performance time series semantic feature vector and the building component usage data semantic feature vector to obtain a building component operation data fusion feature vector; Based on the building component operation data, the feature vector is fused to obtain a judgment result.

7. The method for operation and management of assembled building structures according to claim 6, characterized in that: Based on the sequence of the building component performance time series input vector, a building component performance time series semantic feature vector is obtained, including: Extracting component performance time series features from the sequence of building component performance time series input vectors to obtain a sequence of building component performance time series feature vectors; Data semantic extraction is performed on the sequence of the building component performance time series feature vectors to obtain the building component performance time series semantic feature vectors.

Images