Construction operation supervision and early warning method, device and equipment based on grid management

Abstract

The invention relates to the field of artificial intelligence, and discloses a construction operation supervision and early warning method, device and equipment based on grid management, and the method comprises the steps: obtaining the construction operation data of a construction grid; analyzing and predicting the construction operation data according to a safety risk early warning model so as to judge whether the safety violation risk of the construction grid is greater than a preset risk threshold value or not; and when the safety violation risk of the construction grid is greater than a preset risk threshold, sending out a construction safety risk early warning corresponding to the grid.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence, and in particular to a construction operation supervision and early warning method, device and equipment based on grid management. Background Art

[0002] In recent years, with the expansion of the scale and complexity of construction projects, the risk of production safety accidents has also increased. In order to meet these challenges, the construction industry has gradually promoted grid-based safety management. This management method subdivides the construction work surface into independent grid units through the principle of territorial management, and ensures the implementation of responsibilities through hierarchical management, forming a three-dimensional grid covering all levels of the construction site, aiming to integrate resources and improve the overall level of safety management. However, the existing grid-based safety management technology still has certain problems in specific applications, such as untimely warning, low accuracy, and lack of systematicity. Especially in the real-time monitoring and accident prevention of production safety management, traditional methods that rely on experience judgment and simple rules are difficult to meet the needs of the increasingly complex construction environment. Although the monitoring and early warning models for construction work surfaces have made certain progress, they still face many challenges in practical applications.

[0003] The existing technology has at least the following technical problems:

[0004] Although some advanced early warning models have high accuracy, they are difficult to be widely used in complex and changeable construction sites due to their complex operation and high deployment costs.

[0005] The current early warning model has certain limitations in adapting to different construction environments and conditions, and it is difficult to meet the safety management needs in various scenarios.

[0006] In the existing production safety management, responsibilities are not fully implemented and supervision is difficult, making it impossible to achieve all-weather and all-round monitoring of the construction site, resulting in potential safety hazards being difficult to discover and deal with in a timely manner. Summary of the invention

[0007] In view of this, the present application provides a construction work supervision and early warning method based on grid management to solve the technical problems in the prior art.

[0008] According to a first aspect of the present application, a construction operation supervision and early warning method based on grid management is provided, comprising:

[0009] Acquire construction operation data of the construction grid, wherein the construction operation data includes environmental data, equipment operation data and basic information of construction personnel;

[0010] Analyzing and predicting the construction operation data according to the safety risk early warning model to determine whether the safety violation risk of the construction grid is greater than a preset risk threshold, wherein the safety risk early warning model is trained based on historical construction operation data;

[0011] When the safety violation risk of a construction grid is greater than the preset risk threshold, a construction safety risk warning corresponding to the grid is issued.

[0012] According to a second aspect of the present application, a construction operation supervision and early warning device based on grid management is provided, comprising:

[0013] An acquisition module, used to acquire construction operation data of a construction grid, wherein the construction operation data includes environmental data, equipment operation data and basic information of construction personnel;

[0014] A prediction module is used to analyze and predict the construction operation data according to a safety risk warning model to determine whether the safety violation risk of the construction grid is greater than a preset risk threshold, wherein the safety risk warning model is trained based on historical construction operation data;

[0015] The output module is used to issue a construction safety risk warning corresponding to the grid when the safety violation risk of the construction grid is greater than a preset risk threshold.

[0016] According to the third aspect of the present application, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned construction work supervision and early warning method based on grid management are implemented.

[0017] Through the above-mentioned technical scheme, the present application provides a construction work supervision and early warning method, device, equipment and medium based on grid management, which obtains the construction work data of the construction grid; analyzes and predicts the construction work data according to the safety risk early warning model to determine whether the safety violation risk of the construction grid is greater than the preset risk threshold; when the safety violation risk of the construction grid is greater than the preset risk threshold, a construction safety risk early warning corresponding to the grid is issued.

[0018] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application and to implement it in accordance with the contents of the specification, and to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0020] Figure 1 A schematic diagram of an application scenario of a construction operation supervision and early warning method based on grid management provided in an embodiment of the present application is shown;

[0021] Figure 2 A schematic diagram of a construction operation supervision and early warning method based on grid management provided in an embodiment of the present application is shown;

[0022] Figure 3 A schematic diagram of the network structure of the security risk warning model provided in an embodiment of the present application is shown;

[0023] Figure 4 A structural schematic diagram of a construction work supervision and early warning device based on grid management provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0024] The specific implementation of the present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0025] The embodiment of the present invention provides a construction operation supervision and early warning method based on grid management, which can be applied to Figure 1 In the scenario shown, Figure 1 Through multi-source data collection (environment, equipment, operation data), combined with the basic personnel information database, the system architecture performs intelligent analysis and early warning on the server. The core function of the system is to predict safety hazards at the construction site through real-time data collection and analysis, and improve the safety and efficiency of construction management.

[0026] The collected environmental data includes environmental parameters of the construction site, such as temperature, humidity, air pressure, wind speed, noise, dust concentration, etc. The data is collected in real time through sensors and used to evaluate the safety of the construction environment. Changes in environmental data may affect equipment, personnel and construction progress.

[0027] The collected equipment operation data refers to the status information of the equipment on the construction site, such as the equipment's operating time, load, fault alarm, power consumption, etc. This data is used to monitor the equipment's operating status and predict whether the equipment is likely to fail, so as to perform preventive maintenance or stop the operation of dangerous equipment.

[0028] The collected construction operation data includes specific operations at the construction site, such as construction progress, operation process, personnel deployment, etc. By collecting operation data, the system can analyze whether there are any illegal operations or safety hazards in the current construction activities, and issue early warnings in a timely manner.

[0029] The construction personnel basic information database stores the basic information of all construction personnel, such as their length of service, skill level, violation records, and continuous safe construction days.

[0030] The above data, combined with real-time operating conditions, is used to assess the risk level of construction workers and predict the possibility of violations by workers, thereby improving the accuracy of personnel safety management.

[0031] The server, as a central control unit, is responsible for receiving inputs from the environment, equipment, and construction data, and performing data analysis and processing in combination with the basic information database of construction personnel. Through the server, the safety risk warning model can be applied to analyze the input data to determine whether there are safety hazards at the construction site, and issue a warning when necessary to prompt management personnel to take corresponding measures. The invention provides a construction operation supervision and warning method based on grid management, by obtaining the construction operation data of the construction grid; analyzing and predicting the construction operation data according to the safety risk warning model to determine whether the safety violation risk of the construction grid is greater than the preset risk threshold; when the safety violation risk of the construction grid is greater than the preset risk threshold, a construction safety risk warning corresponding to the grid is issued.

[0032] The present invention is described in detail below through specific embodiments.

[0033] Embodiment 1:

[0034] like Figure 2 As shown, a construction operation supervision and early warning method based on grid management is provided in an embodiment of the present invention, comprising:

[0035] Step 201, obtaining construction operation data of the construction grid;

[0036] Among them, construction operation data includes environmental data, equipment operation data and basic information of construction personnel;

[0037] Step 202: Analyze and predict the construction operation data according to the safety risk early warning model to determine whether the safety violation risk of the construction grid is greater than a preset risk threshold;

[0038] Among them, the safety risk warning model is obtained by training based on historical construction operation data;

[0039] Step 203: When the safety violation risk of the construction grid is greater than a preset risk threshold, a construction safety risk warning corresponding to the grid is issued.

[0040] A construction operation supervision and early warning method based on grid management is provided in a first embodiment of the present invention, which obtains construction operation data of a construction grid; analyzes and predicts the construction operation data according to a safety risk early warning model to determine whether the safety violation risk of the construction grid is greater than a preset risk threshold; when the safety violation risk of the construction grid is greater than the preset risk threshold, a construction safety risk early warning corresponding to the grid is issued.

[0041] By continuously monitoring the real-time data of the construction grid, potential safety hazards can be discovered quickly and in real time. The safety management methods of the prior art usually rely on manual inspections and experience judgments, which are lagging. The method of the first embodiment of the present invention can achieve real-time monitoring and timely warning through automated data collection and analysis, greatly improving the response speed of construction management and effectively avoiding the occurrence of safety accidents. By analyzing and predicting the construction operation data based on the safety risk warning model, the safety risks in the construction process can be accurately identified. When the safety violation risk of the construction grid exceeds the preset threshold, the system will automatically issue a safety warning. The automated warning mechanism reduces the need for manual intervention and improves the efficiency of construction safety management. Through automatic warning, managers can obtain risk notifications in a timely manner and take corresponding safety measures immediately to ensure the safety of construction personnel and equipment. Through automated data collection and model prediction, mistakes and omissions in traditional manual management are avoided. Through effective risk prediction and timely warning, the present invention can significantly reduce the occurrence of safety accidents. Before the safety violation risk of the construction grid reaches the preset risk threshold, a warning is issued in a timely manner to remind managers to intervene and deal with it, which greatly reduces the probability of safety accidents and ensures the safety of construction personnel and equipment.

[0042] Embodiment 2:

[0043] Compared with the first embodiment, the security risk warning model training is performed in advance. Accordingly, the security risk warning model training is included before step 202, which specifically includes:

[0044] Step 202-1, obtaining historical construction operation data, basic information of construction personnel and violation data of construction personnel;

[0045] Step 202-2: inputting historical construction operation data and basic information of construction personnel into the convolutional neural network model to obtain the convolutional neural network model output;

[0046] The convolutional neural network model includes a convolutional layer, a pooling layer, and a fully connected layer. Before each convolutional layer, Gaussian noise is added to the input data x to generate new input data x′, or, after each convolutional layer, Gaussian noise is added to the output data f to generate new output data f′, where: is Gaussian noise with zero mean and variance σ. The output feature vector of each convolutional layer is pooled and Gaussian noise is added at the same time, wherein the pooling operation includes maximum pooling or average pooling. Gaussian noise is added to the input feature vector of the fully connected layer, the input feature vector with noise is linearly transformed, and the classification result is generated through the activation function.

[0047] Step 202-3, calculating the value of the loss function to evaluate the difference between the output of the convolutional neural network model and the corresponding construction worker violation data;

[0048] Among them, the loss function Among them, L main is the main loss function, usually the cross entropy loss function, which measures the gap between the probability distribution predicted by the model and the true label. is the auxiliary loss function of the kth layer, and λ is the weight of the auxiliary loss function used to control the balance between the main loss function and the auxiliary loss function. In the convolutional neural network of the second embodiment of the present invention, the additional loss term introduced by the auxiliary loss of each layer is used to help the network learn in the process of processing noise at each layer, and ensure that the model can still effectively extract features even in a noisy environment. The main purpose of the auxiliary loss is to guide the network to learn the denoising ability layer by layer, rather than relying solely on the final global loss. The auxiliary loss includes the auxiliary loss of the convolution layer, the auxiliary loss of the pooling layer, and the auxiliary loss of the fully connected layer. Each layer of auxiliary loss imposes supervision on the noisy data to ensure that the model can not only cope with the final task, but also gradually learn the denoising function in the intermediate layers. The design of the auxiliary loss is based on the cross entropy loss of the classification task. The network weights are optimized by gradient descent, so that the model has good robustness and generalization ability in a noisy environment.

[0049] Step 202-4: When the loss function value is less than a preset threshold or the number of iterations is greater than a preset number, the convolutional neural network is output as a security risk warning model.

[0050] In the second embodiment of the present invention, a self-denoising mechanism is added, noise is added to each convolution layer or pooling layer, and training is performed through an auxiliary loss function, so that the network can enhance the robustness to noise and extract more accurate features. Layer-by-layer noise injection and denoising add noise to each layer of the convolution network (e.g., one-dimensional convolution layer, two-dimensional convolution layer) for data features in different grids. This allows the model to learn to process noise in different feature spaces, thereby improving the robustness of feature extraction and the ability to identify potential safety hazards. An auxiliary loss function is added after each convolution layer to ensure that the network can still maintain the ability to identify safety hazards even under the influence of noise. The auxiliary loss function can use a cross entropy loss function. The auxiliary loss function can help the network learn useful features at an early level, thereby improving the convergence speed and classification performance of the model, especially when processing small sample data. The auxiliary loss function can prevent overfitting to a certain extent, calculate the error between the classification result output by each layer and the true label, and optimize the network weights through gradient descent, effectively improving the accuracy of construction safety risk warning.

[0051] Compared with the prior art, the second embodiment of the present invention dynamically introduces noise at different levels of the network, and uses an auxiliary loss function to allow the model to gradually learn the ability to remove noise during training. This dynamic noise processing mechanism enables the model to adapt to noise of different types and intensities, effectively improving the robustness and anti-interference ability of the model in complex environments.

[0052] Further, as Figures 2 to 3 In the specific implementation of the method, the present invention provides a construction operation supervision and early warning device based on grid management, such as Figure 4 As shown, the device comprises:

[0053] An acquisition module 410 is used to acquire construction operation data of a construction grid, wherein the construction operation data includes environmental data, equipment operation data and basic information of construction personnel;

[0054] Prediction module 420, used to analyze and predict the construction operation data according to the safety risk warning model to determine whether the safety violation risk of the construction grid is greater than a preset risk threshold, wherein the safety risk warning model is trained based on historical construction operation data;

[0055] The output module 430 is used to issue a construction safety risk warning corresponding to the grid when the safety violation risk of the construction grid is greater than a preset risk threshold.

[0056] In an embodiment of the present invention, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of implementing a construction operation supervision and early warning method based on grid management include:

[0057] Acquire construction operation data of the construction grid, wherein the construction operation data includes environmental data, equipment operation data and basic information of construction personnel;

[0058] Analyzing and predicting the construction operation data according to the safety risk early warning model to determine whether the safety violation risk of the construction grid is greater than a preset risk threshold, wherein the safety risk early warning model is trained based on historical construction operation data;

[0059] When the safety violation risk of a construction grid is greater than the preset risk threshold, a construction safety risk warning corresponding to the grid is issued.

[0060] It should be noted that the above embodiments only use the construction grid management scenario as an example to illustrate the principles and implementation steps of the embodiments of the present invention, which can be applied to a variety of scenarios, especially industries and fields that require continuous monitoring, rapid response and security management. There is no specific limitation on the actual application scenarios, such as urban infrastructure management, intelligent transportation systems, power facility operation and maintenance, smart factories and industrial equipment management, etc. For the functions or steps that can be implemented by computer-readable storage media or computer devices, please refer to the aforementioned method embodiments. To avoid repetition, they will not be described one by one here.

[0061] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0062] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0063] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A construction operation supervision and early warning method based on grid management, characterized in that: include: Acquire construction operation data of the construction grid, wherein the construction operation data includes environmental data, equipment operation data and basic information of construction personnel; Analyzing and predicting the construction operation data according to the safety risk early warning model to determine whether the safety violation risk of the construction grid is greater than a preset risk threshold, wherein the safety risk early warning model is trained based on historical construction operation data; When the safety violation risk of a construction grid is greater than the preset risk threshold, a construction safety risk warning corresponding to the grid is issued.

2. The construction operation supervision and early warning method based on grid management according to claim 1 is characterized in that: Before the step of analyzing and predicting the construction operation data according to the safety risk early warning model to determine whether the safety violation risk of the construction grid is greater than a preset risk threshold, the method includes: Obtain historical construction operation data, basic information of construction personnel, and data on violations of construction personnel; Input historical construction operation data and basic information of construction personnel into the convolutional neural network model to obtain the convolutional neural network model output; Calculate the loss function value to evaluate the difference between the output of the convolutional neural network model and the corresponding construction workers’ violation data; When the loss function value is less than a preset threshold or the number of iterations is greater than a preset number, the convolutional neural network is output as a safety risk warning model.

3. The construction operation supervision and early warning method based on grid management according to claim 2 is characterized in that: The convolutional neural network model includes a convolutional layer, a pooling layer and a fully connected layer.

4. The construction operation supervision and early warning method based on grid management according to claim 3 is characterized in that: Before each convolution layer, Gaussian noise is added to the input data x to generate new input data x′, or, after each convolution layer, Gaussian noise is added to the output data f to generate new output data f′, where, is Gaussian noise with zero mean and variance σ.

5. The construction operation supervision and early warning method based on grid management according to claim 3 is characterized in that: A pooling operation is performed on the output feature vector of each convolutional layer and Gaussian noise is added at the same time, wherein the pooling operation includes maximum pooling or average pooling.

6. The construction operation supervision and early warning method based on grid management according to claim 3 is characterized in that: Gaussian noise is added to the input feature vector of the fully connected layer, the noisy input feature vector is linearly transformed, and the classification result is generated through the activation function.

7. The construction operation supervision and early warning method based on grid management according to claim 3 is characterized in that: Loss Function Among them, L main is the main loss function, is the auxiliary loss function of the kth layer, and λ is the weight of the auxiliary loss function, which is used to control the balance between the main loss function and the auxiliary loss function.

8. A construction operation supervision and early warning device based on grid management, characterized in that: include: An acquisition module, used to acquire construction operation data of a construction grid, wherein the construction operation data includes environmental data, equipment operation data and basic information of construction personnel; A prediction module is used to analyze and predict the construction operation data according to a safety risk warning model to determine whether the safety violation risk of the construction grid is greater than a preset risk threshold, wherein the safety risk warning model is trained based on historical construction operation data; The output module is used to issue a construction safety risk warning corresponding to the grid when the safety violation risk of the construction grid is greater than a preset risk threshold.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the construction work supervision and early warning method based on grid management as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, the steps of the construction work supervision and early warning method based on grid management as described in any one of claims 1 to 7 are implemented.

Images