Decoration engineering project risk assessment system based on artificial intelligence
The decoration engineering project risk assessment system uses AI to model demolition processes, predict vibration intensity and debris trajectories, and score risks, addressing the challenge of unpredictable damage in decoration projects by accurately identifying high-risk areas and reducing associated costs.
Patent Information
- Application Number
- CN202411265735.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-10
- Publication Date
- 2024-12-24
- Estimated Expiration
- 2044-09-10
Smart Images
Figure CN118798656B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of risk assessment, and in particular to a risk assessment system for decoration engineering projects based on artificial intelligence. Background Art
[0002] Artificial intelligence decoration project risk assessment is a tool that uses modern technology to analyze and manage potential risks in decoration projects. Through these functions, it can help project managers more accurately predict and respond to potential risks. When the decoration project is to demolish walls and transform the space of an old house, due to the presence of decorated tiles and wallpaper around the wall, a hammer is used to hammer the wall, and vibration fluctuations and vibration fluctuation areas are generated, resulting in the risk of damage caused by vibration intensity exceeding the tiles or wallpaper. Therefore, the vibration intensity of the vibration fluctuation area cannot be predicted in detail, and the impact of vibration on the entire decoration project during the actual decoration transformation process cannot be accurately reflected, so it is impossible to provide a more realistic risk assessment. At the same time, the debris generated by smashing the wall will lead to the risk of furniture damage, increasing the cost of furniture repair and replacement. Therefore, we provide a decoration project risk assessment system based on artificial intelligence. Summary of the invention
[0003] The purpose of the present invention is to provide a decoration engineering project risk assessment system based on artificial intelligence to solve the problems raised in the above background technology.
[0004] To achieve the above-mentioned purpose, the present invention provides a decoration engineering project risk assessment system based on artificial intelligence, comprising a model area unit, a vibration assessment unit, a data prediction unit, a risk assessment unit, and a project risk scoring unit;
[0005] The model area unit acquires historical data and establishes a decoration engineering model. The decoration engineering model forms image data of the wall to be demolished, and then discretizes the wall into a number of points. When the hammer strikes a plurality of points on the wall surface randomly, the peripheral points spread outward and connect to form a vibration fluctuation area.
[0006] The vibration assessment unit is used to receive data in the model area unit and calculate the vibration fluctuation distance, predict the vibration intensity of all hammer strikes superimposed in the vibration fluctuation area according to the data in the model area unit and the vibration fluctuation distance, and then use the superimposed vibration intensity in the vibration fluctuation area and the vibration resistance strength of the tiles to assess the damage risk to the tiles caused by the superimposed vibration intensity in the vibration fluctuation area;
[0007] The data prediction unit is used to receive data from the vibration assessment unit and the model area unit, regard the wall debris as a number of points in the demolished wall, and predict different movement trajectories of the falling points based on the data from the vibration assessment unit and the model area unit;
[0008] The risk assessment unit is used to receive data from the data prediction unit and the model area unit, and when different motion trajectories of the falling points pass through the placed furniture, all the points passing through the furniture are screened out, and the damage risk of the wall debris to the furniture is assessed according to the number of points passing through the furniture;
[0009] The project risk scoring unit is used to receive the damage risk to tiles caused by the vibration intensity assessed in the vibration assessment unit and the damage risk to furniture caused by wall debris assessed in the risk assessment unit, and to perform risk indicator scoring for the decoration project.
[0010] As a further improvement of the technical solution, the model region unit includes a learning model module, a fluctuation region module and an intersection region module;
[0011] The learning model module learns the decoration project through the machine learning technology in artificial intelligence, and obtains historical data. The decoration project model is established according to the decoration project data and historical data. The decoration project model forms the image data of the wall to be demolished and the environmental image data around the wall. The wall is then discretized into several points using a discretization algorithm. At the same time, the hammer striking surface is extracted from the decoration project data, and the hammer striking surface is used to randomly hammer multiple points on the wall surface. The hammer striking force and the number of hammer strikes are then recorded. At this time, when the hammer striking surface covers multiple points on the wall surface, vibration fluctuations are generated, and the corresponding coordinates of the covered multiple points and the number of covered points are recorded.
[0012] The fluctuation area module is used to receive command data for generating vibration fluctuations in the learning model module. The fluctuation area module obtains multiple covered points from the learning model module. When the multiple covered points detect the generated vibration fluctuations, the points on the periphery of the coverage diffuse outward along with the vibration fluctuations, stop when there is no vibration, and connect the points on the periphery of the diffusion to form a vibration fluctuation area. By diffusing and connecting the peripheral points, the regional boundary of the vibration fluctuation can be accurately defined, thereby obtaining a clear vibration impact area;
[0013] The intersection area module is used to receive the vibration fluctuation area in the fluctuation area module and the decoration project data in the learning model module, extract the decorated tile area around the wall from the decoration project data, and intersect the vibration fluctuation area with the decorated tile area around the wall to obtain the intersection area, and then extract the points that exist in the diffusion periphery of the intersection area.
[0014] As a further improvement of the technical solution, the vibration assessment unit includes a vibration intensity module and a damage assessment module;
[0015] The vibration intensity module is used to receive the hammer force, hammer number, number of covered points, multiple covered points and corresponding coordinates, and historical data in the learning model module, receive the points in the intersection area in the fluctuation area module, extract pi, density of wall materials, and sound speed data of wall materials from the historical data, and then use the center point of multiple covered points and the point in the intersection area to calculate the vibration fluctuation distance, and predict the vibration intensity of all hammer superimposed in the vibration fluctuation area according to the hammer force, hammer number, number of covered points, pi, density of wall materials, sound speed of wall materials and vibration fluctuation distance, and make a detailed prediction of the vibration intensity of the vibration fluctuation area, which can more accurately identify potential high-risk areas and impact levels, avoid excessive or insufficient risk assessment, and can accurately reflect the overall impact of the superposition of multiple vibration sources in the actual construction process, thereby providing a more realistic risk assessment;
[0016] The damage assessment module is used to receive the superimposed vibration intensity in the vibration fluctuation area in the vibration intensity module and the intersection area in the intersection area module, receive the vibration resistance of the tiles in the learning model module, and use the superimposed vibration intensity in the vibration fluctuation area and the vibration resistance of the tiles to evaluate the tiles in the intersection area, and evaluate the damage risk to the tiles caused by the superimposed vibration intensity in the vibration fluctuation area. By evaluating the damage risk to the tiles, it can be accurately determined which tiles are in high-risk areas. Detailed analysis helps to identify the tiles that are most vulnerable to damage in the vibration fluctuation area, thereby more effectively assessing potential damage risks.
[0017] As a further improvement of the technical solution, the vibration intensity module predicts the vibration intensity of all hammer strikes superimposed in the vibration fluctuation area to achieve the following principle:
[0018] Collect hammer strength , hammering times M, number of coverage points , Pi , density of wall materials , the sound velocity of the wall material The vibration intensity of all hammer strikes in the vibration fluctuation area is calculated by calculating the vibration intensity of the superposition of all hammer strikes in the vibration fluctuation area to obtain the superimposed vibration intensity. That is to predict the vibration intensity of all hammer strikes superimposed in the vibration fluctuation area. The specific algorithm formula is:
[0019] ;
[0020] in, Refers to the center point to the The square of the distance between the points in the intersection area, It refers to the force of the i-th hammer blow. This formula is used to predict the vibration intensity of all the superimposed hammer blows in the vibration fluctuation area. By predicting the vibration intensity of all the superimposed hammer blows, we can fully understand the impact of vibration on the entire decoration project and avoid considering only a single vibration source.
[0021] As a further improvement of the technical solution, the data prediction unit includes a data recording module and a prediction trajectory module;
[0022] The data recording module is used to receive the predicted superimposed vibration intensity in the vibration intensity module and the vibration resistance of the demolished wall in the learning model module. When the predicted superimposed vibration intensity is greater than the vibration resistance of the demolished wall, it means that the demolished wall will be shattered and wall debris will fall. Since the wall is discretized into several points, and the wall debris is regarded as several points in the demolished wall, when the point falls, the corresponding resistance coefficient, point falling speed and falling time, and the cross-sectional area of the shattered wall are recorded. The wall is regarded as multiple points, making it possible to independently analyze the damage of each point, so that the degree of damage and the distribution of wall debris in different areas can be evaluated;
[0023] The prediction trajectory module is used to receive the resistance coefficient, point drop speed, point drop time and cross-sectional area of the broken wall in the data recording module, receive the historical data in the learning model module, extract the gravity acceleration, the mass of the wall material, the air density, the direction of the air resistance and the direction of gravity from the historical data, and use the resistance coefficient, point drop speed, point drop time, the cross-sectional area of the broken wall, the gravity acceleration, the air density and the direction of the air resistance to predict the different movement trajectories of the point drop. By predicting the movement trajectory of the point drop, it is possible to analyze in detail which areas will be directly affected by the wall debris and accurately identify the high-risk areas of the furniture. At the same time, accurately predicting the movement trajectory of the wall debris can effectively reduce damage to furniture and other items, thereby reducing the cost of repair or replacement.
[0024] As a further improvement of the technical solution, the steps for implementing different motion trajectories of predicted point drops in the predicted trajectory module are as follows:
[0025] Step 1: Obtain the resistance coefficient , point drop speed , click drop time , the cross-sectional area of the crushed wall , Gravitational acceleration , the quality of wall materials , air density , the direction of air resistance and the direction of gravity. The direction of air resistance is opposite to the direction of velocity. According to the direction of air resistance and velocity, the unit vector of velocity is derived. ;
[0026] Step 2: Use differential symbols Utilize point drop speed and point drop time Get the acceleration of the point , refers to a vector representing the rate of change of the point velocity;
[0027] Step 3: Use gravity acceleration , the quality of wall materials (kg) and the direction of gravity (Also referred to as a unit vector, for vertical fall, it is usually a unit vector pointing downward (such as )) Obtain the gravity term ;
[0028] Step 4: Use air density (Unit: kg / , the commonly used air density value is 1.225kg / ), drag coefficient , the cross-sectional area of the crushed wall (unit: ) and the unit vector of velocity The air resistance term , the specific algorithm formula is:
[0029] ;
[0030] in, is a constant used to adjust the scale of the air resistance formula, Refers to the square of the point drop speed (unit: );
[0031] Step 5: Acceleration of the passing point , Gravity and the air resistance term The different motion trajectories of the calculated point drop are the different motion trajectories of the predicted point drop. The specific algorithm formula is:
[0032] ;
[0033] Among them, this formula is used to predict the different movement trajectories of point drops. By predicting the movement trajectory of point drops, it is possible to analyze in detail which areas will be directly affected by wall debris, which helps to accurately identify high-risk areas of furniture.
[0034] As a further improvement of the present technical solution, the risk assessment unit is used to receive different motion trajectories of point drops in the prediction trajectory module and the furniture placed in the decoration project data of the learning model module. When the different motion trajectories of the point drops pass through the placed furniture, it indicates that the wall debris will hit the placed furniture, and all points passing through the furniture are screened out, and the number of points is recorded. The risk of damage to the furniture caused by the wall debris is assessed based on the number of points passing through the furniture (that is, the number of wall debris). By calculating the number of points passing through the furniture (that is, the number of wall debris), the risk of the wall debris to the furniture can be quantified. This quantitative analysis is more accurate than traditional qualitative assessment and can provide specific risk data.
[0035] As a further improvement of the present technical solution, the project risk scoring unit is used to receive the damage risk to tiles caused by the vibration intensity assessed in the damage assessment module and the damage risk to furniture caused by wall debris assessed in the risk assessment unit. The decoration engineering model scores the risk indicators of the decoration engineering project according to the assessed damage risk to tiles caused by the vibration intensity and the assessed damage risk to furniture caused by wall debris. By comprehensively considering the impact of vibration intensity and wall debris on furniture, the risks in the decoration engineering project can be evaluated more comprehensively, avoiding the neglect of a single factor, and the scoring of risk indicators can be visualized.
[0036] Compared with the prior art, the present invention has the following beneficial effects:
[0037] 1. In the risk assessment system of the decoration engineering project of the artificial intelligence, the vibration intensity module is used to receive the hammer force, the number of hammer blows, the number of covered points, the multiple covered points and the corresponding coordinates, and the historical data in the learning model module, receive the points with intersection areas in the fluctuation area module, extract the pi, the density of the wall material, and the sound speed data of the wall material from the historical data, and then use the center point of the multiple points covered and the point with intersection area to calculate the vibration fluctuation distance, and predict the vibration intensity of all the hammers superimposed in the vibration fluctuation area according to the hammer force, the number of hammer blows, the number of covered points, pi, the density of the wall material, the sound speed of the wall material and the vibration fluctuation distance, and make a detailed prediction of the vibration intensity of the vibration fluctuation area, which can more accurately identify potential high-risk areas and the degree of impact, avoid excessive or insufficient risk assessment, and can accurately reflect the overall impact of the superposition of multiple vibration sources in the actual construction process, thereby providing a more realistic risk assessment.
[0038] 2. In the risk assessment system of the decoration engineering project of the artificial intelligence, the prediction trajectory module is used to receive the resistance coefficient, point drop speed, point drop time and the cross-sectional area of the broken wall in the data recording module, receive the historical data in the learning model module, extract the gravity acceleration, the mass of the wall material, the air density, the direction of the air resistance and the gravity direction from the historical data, and use the resistance coefficient, point drop speed, point drop time, the cross-sectional area of the broken wall, the gravity acceleration, the air density and the direction of the air resistance to predict the different movement trajectories of the point drop. By predicting the movement trajectory of the point drop, it is possible to analyze in detail which areas will be directly affected by the wall debris and accurately identify the high-risk areas of the furniture. At the same time, accurately predicting the movement trajectory of the wall debris can effectively reduce damage to furniture and other items, thereby reducing the cost of repair or replacement. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] Figure 1 is an overall block diagram of the present invention;
[0040] Figure 2 It is a block diagram of the model area unit of the present invention;
[0041] Figure 3 It is a block diagram of the vibration evaluation unit of the present invention;
[0042] Figure 4 This is a block diagram of the data prediction unit of the present invention.
[0043] The meaning of each number in the figure is:
[0044] 1. Model area unit; 11. Learning model module; 12. Fluctuation area module; 13. Intersection area module;
[0045] 2. Vibration assessment unit; 21. Vibration intensity module; 22. Damage assessment module;
[0046] 3. Data prediction unit; 31. Data recording module; 32. Prediction trajectory module;
[0047] 4. Risk assessment unit; 5. Project risk scoring unit. DETAILED DESCRIPTION
[0048] The following will be combined with the accompanying drawings in the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention. Example
[0049] The present invention provides a decoration engineering project risk assessment system based on artificial intelligence, please refer to Figure 1-Figure 4 , including a model area unit 1, a vibration assessment unit 2, a data prediction unit 3, a risk assessment unit 4, and a project risk scoring unit 5;
[0050] The model area unit 1 obtains historical data and establishes a decoration engineering model. The decoration engineering model forms the image data of the wall to be demolished, and then discretizes the wall into a number of points. When the hammer strikes the surface of the wall randomly, the peripheral points spread outward and connect to form a vibration fluctuation area.
[0051] The vibration assessment unit 2 is used to receive the data in the model area unit 1 and calculate the vibration fluctuation distance, predict the vibration intensity of all hammer strikes superimposed in the vibration fluctuation area according to the data in the model area unit 1 and the vibration fluctuation distance, and then use the superimposed vibration intensity in the vibration fluctuation area and the vibration resistance strength of the tiles to assess the damage risk to the tiles caused by the superimposed vibration intensity in the vibration fluctuation area;
[0052] The data prediction unit 3 is used to receive the data in the vibration assessment unit 2 and the model area unit 1, regard the wall debris as a number of points in the demolished wall, and predict different movement trajectories of the falling points according to the data in the vibration assessment unit 2 and the model area unit 1;
[0053] The risk assessment unit 4 is used to receive the data in the data prediction unit 3 and the model area unit 1, and when different motion trajectories of the falling points pass through the placed furniture, all the points passing through the furniture are screened out, and the damage risk of the wall debris to the furniture is assessed according to the number of points passing through the furniture;
[0054] The project risk scoring unit 5 is used to receive the damage risk of tiles caused by the vibration intensity assessed by the vibration assessment unit 2 and the damage risk of furniture caused by wall debris assessed by the risk assessment unit 4, and to perform risk indicator scoring for the decoration project.
[0055] The following is a refinement of the above units, see Figure 1-Figure 4 ;
[0056] The model region unit 1 includes a learning model module 11, a fluctuation region module 12 and an intersection region module 13;
[0057] The learning model module 11 learns the decoration project through the machine learning technology in artificial intelligence, and obtains historical data, and establishes a decoration project model according to the decoration project data and the historical data. The decoration project model forms the image data of the wall to be demolished and the environmental image data around the wall, and then uses the discretization algorithm to discretize the wall into a number of points. At the same time, the hammer striking surface is extracted from the decoration project data, and the hammer striking surface is used to randomly hammer multiple points on the wall surface, and then the hammering force and the number of hammering times are recorded. At this time, when the hammer striking surface covers multiple points on the wall surface, vibration fluctuations are generated, and the corresponding coordinates of the covered multiple points and the number of covered points are recorded at the same time;
[0058] The decoration project includes the image data of the wall to be demolished (the demolished wall is a non-load-bearing wall), the image data of the environment around the wall (including the tiles and furniture decorated around the wall), and the decoration tools (hammer);
[0059] Historical data includes pi, density of wall material, speed of sound and mass, vibration resistance of tiles and demolished walls, gravitational acceleration, air density, direction of air resistance and direction of gravity;
[0060] The fluctuation area module 12 is used to receive command data for generating vibration fluctuations in the learning model module 11. The fluctuation area module 12 obtains multiple covered points from the learning model module 11. When the multiple covered points detect the generated vibration fluctuations, the points on the periphery of the coverage diffuse outward along with the vibration fluctuations, stop when there is no vibration, and connect the points on the periphery of the diffusion to form a vibration fluctuation area. By diffusing and connecting the peripheral points, the regional boundary of the vibration fluctuations can be accurately defined, thereby obtaining a clear vibration impact area;
[0061] The intersection area module 13 is used to receive the vibration fluctuation area in the fluctuation area module 12 and the decoration project data in the learning model module 11, extract the decorated tile area around the wall from the decoration project data, and intersect the vibration fluctuation area with the decorated tile area around the wall to obtain the intersection area, and then extract the points that exist in the diffusion periphery of the intersection area;
[0062] The vibration assessment unit 2 includes a vibration intensity module 21 and a damage assessment module 22;
[0063] The vibration intensity module 21 is used to receive the hammer force, hammer number, number of covered points, multiple covered points and corresponding coordinates, and historical data in the learning model module 11, receive the points in the intersection area in the fluctuation area module 12, extract pi, density of wall materials, and sound speed data of wall materials from the historical data, and then use the center point of the multiple points covered and the point in the intersection area to calculate the vibration fluctuation distance, and predict the vibration intensity of all hammer superimposed in the vibration fluctuation area according to the hammer force, hammer number, number of covered points, pi, density of wall materials, sound speed of wall materials and vibration fluctuation distance, and make a detailed prediction of the vibration intensity of the vibration fluctuation area, so as to more accurately identify potential high-risk areas and the degree of impact, avoid excessive or insufficient risk assessment, and accurately reflect the overall impact of the superposition of multiple vibration sources in the actual construction process, thereby providing a more realistic risk assessment;
[0064] The principle of predicting the vibration intensity of all hammer strikes superimposed in the vibration fluctuation area:
[0065] Collect hammer strength , hammering times M, number of coverage points , Pi , density of wall materials , the sound velocity of the wall material The vibration intensity of all hammer strikes in the vibration fluctuation area is calculated by calculating the vibration intensity of the superposition of all hammer strikes in the vibration fluctuation area to obtain the superimposed vibration intensity. That is to predict the vibration intensity of all hammer strikes superimposed in the vibration fluctuation area. The specific algorithm formula is:
[0066] ;
[0067] in, Refers to the center point to the The square of the distance between the points in the intersection area, Refers to the strength of the hammer strike at the ith time. This formula is used to predict the vibration intensity of all hammer strikes superimposed in the vibration fluctuation area. By predicting the vibration intensity of all hammer strikes superimposed, we can fully understand the impact of vibration on the entire decoration project and avoid considering only a single vibration source.
[0068] The damage assessment module 22 is used to receive the superimposed vibration intensity in the vibration fluctuation area in the vibration intensity module 21 and the intersection area in the intersection area module 13, receive the vibration resistance of the tiles in the learning model module 11, and use the superimposed vibration intensity in the vibration fluctuation area and the vibration resistance of the tiles to evaluate the damage risk to the tiles caused by the superimposed vibration intensity in the vibration fluctuation area. By evaluating the damage risk to the tiles, it is possible to accurately determine which tiles are in a high-risk area. Detailed analysis helps to identify the tiles that are most vulnerable to damage in the vibration fluctuation area, thereby more effectively evaluating potential damage risks.
[0069] When the superimposed vibration intensity in the vibration fluctuation area is greater than the vibration resistance of the tile, the damage risk of the tile caused by the superimposed vibration intensity in the vibration fluctuation area is evaluated;
[0070] When the superimposed vibration intensity in the vibration fluctuation region is less than or equal to the vibration resistance of the tile, it is assessed that the superimposed vibration intensity in the vibration fluctuation region does not cause a risk of damage to the tile.
[0071] The data prediction unit 3 includes a data recording module 31 and a prediction trajectory module 32;
[0072] The data recording module 31 is used to receive the predicted superimposed vibration intensity in the vibration intensity module 21 and the vibration resistance of the demolished wall in the learning model module 11. When the predicted superimposed vibration intensity is greater than the vibration resistance of the demolished wall, it means that the demolished wall will be shattered and wall debris will fall. Since the wall is discretized into a number of points, and the wall debris is regarded as a number of points in the demolished wall, when the point falls, the corresponding resistance coefficient, point falling speed and falling time, and the cross-sectional area of the shattered wall are recorded. The wall is regarded as multiple points, making it possible to independently analyze the damage of each point, so that the degree of damage and the distribution of wall debris in different areas can be evaluated;
[0073] The prediction trajectory module 32 is used to receive the resistance coefficient, point drop speed, point drop time and cross-sectional area of the broken wall in the data recording module 31, receive the historical data in the learning model module 11, extract the gravity acceleration, the mass of the wall material, the air density, the direction of the air resistance and the gravity direction from the historical data, and use the resistance coefficient, point drop speed, point drop time, the cross-sectional area of the broken wall, the gravity acceleration, the air density and the direction of the air resistance to predict different movement trajectories of the point drop. By predicting the movement trajectory of the point drop, it is possible to analyze in detail which areas will be directly affected by the wall debris and accurately identify the high-risk areas of the furniture. At the same time, accurately predicting the movement trajectory of the wall debris can effectively reduce the damage to the furniture and other items, thereby reducing the cost of repair or replacement;
[0074] Steps to implement different motion trajectories of predicted point drops:
[0075] Step 1: Obtain the resistance coefficient , point drop speed , click drop time , the cross-sectional area of the crushed wall , Gravitational acceleration , the quality of wall materials , air density , the direction of air resistance and the direction of gravity. The direction of air resistance is opposite to the direction of velocity. According to the direction of air resistance and velocity, the unit vector of velocity is derived. ;
[0076] Step 2: Use differential symbols Utilize point drop speed and point drop time The acceleration of the point , refers to a vector representing the rate of change of the point velocity;
[0077] Step 3: Use gravity acceleration , the quality of wall materials (kg) and the direction of gravity (Also referred to as a unit vector, for vertical fall, it is usually a unit vector pointing downward (such as )) Obtain the gravity term ;
[0078] Step 4: Use air density (Unit: kg / , the commonly used air density value is 1.225kg / ), drag coefficient , the cross-sectional area of the crushed wall (unit: ) and the unit vector of velocity The air resistance term , the specific algorithm formula is:
[0079] ;
[0080] in, is a constant used to adjust the scale of the air resistance formula, Refers to the square of the point drop speed (unit: );
[0081] Step 5: Acceleration of the passing point , Gravity and the air resistance term The different motion trajectories of the calculated point drop are the different motion trajectories of the predicted point drop. The specific algorithm formula is:
[0082] ;
[0083] Among them, this formula is used to predict the different movement trajectories of point drops. By predicting the movement trajectories of point drops, it is possible to analyze in detail which areas will be directly affected by wall debris, which helps to accurately identify high-risk areas of furniture;
[0084] The risk assessment unit 4 is used to receive different motion trajectories of point drops in the prediction trajectory module 32 and the furniture placed in the decoration project data of the learning model module 11. When the different motion trajectories of the point drops pass through the placed furniture, it means that the wall debris will hit the placed furniture, and all points passing through the furniture are screened out, and the number of points is recorded. The risk of damage to the furniture caused by the wall debris is assessed based on the number of points passing through the furniture (that is, the number of wall debris). By calculating the number of points passing through the furniture (that is, the number of wall debris), the risk of the wall debris to the furniture can be quantified. This quantitative analysis is more accurate than traditional qualitative evaluation and can provide specific risk data.
[0085] The project risk scoring unit 5 is used to receive the damage risk to tiles caused by the vibration intensity assessed in the damage assessment module 22 and the damage risk to furniture caused by wall debris assessed in the risk assessment unit 4. The decoration engineering model scores the risk indicators of the decoration engineering project according to the assessed damage risk to tiles caused by the vibration intensity and the assessed damage risk to furniture caused by the wall debris. By comprehensively considering the impact of the vibration intensity and the wall debris on furniture, the risks in the decoration engineering project can be evaluated more comprehensively, avoiding the neglect of a single factor, and the scoring of the risk indicators can be visualized.
[0086] Usage process:
[0087] When the fluctuation area module 12 detects the generated vibration fluctuation, the points covering the periphery diffuse outward along with the vibration fluctuation to form a vibration fluctuation area, and the vibration fluctuation area is transmitted to the intersection area module 13. The intersection area module 13 receives the tile area decorated around the wall in the learning model module 11, and intersects the vibration fluctuation area with the tile area decorated around the wall, extracts the points in the intersection area that diffuse outward, and transmits the points in the intersection area to the vibration intensity module 21. The vibration intensity module 21 receives the data in the learning model module 11, and uses the data in the learning model module 11 to calculate the vibration intensity. The vibration fluctuation distance is calculated based on the points with the intersection area, and then the vibration intensity of all hammer strikes superimposed in the vibration fluctuation area is predicted based on the data in the learning model module 11 and the vibration fluctuation distance, and the superimposed vibration intensity in the vibration fluctuation area is transmitted to the damage assessment module 22. The damage assessment module 22 receives the intersection area in the intersection area module 13 and the vibration resistance of the tiles in the learning model module 11, and uses the superimposed vibration intensity in the vibration fluctuation area and the vibration resistance of the tiles in the middle to evaluate the tiles in the intersection area, and evaluate the damage risk of the tiles caused by the superimposed vibration intensity in the vibration fluctuation area;
[0088] The data recording module 31 receives the predicted superimposed vibration intensity in the vibration intensity module 21 and the vibration resistance of the demolished wall by the learning model module 11, and regards the wall debris as several points in the demolished wall. When the point falls, the corresponding resistance coefficient, point falling speed and falling time, and the cross-sectional area of the shattered wall are recorded, and the resistance coefficient, point falling speed, point falling time and the cross-sectional area of the shattered wall are transmitted to the prediction trajectory module 32. The prediction trajectory module 32 receives the historical data in the learning model module 11, and uses the data in the prediction trajectory module 32 and the historical data to predict different motion trajectories of the point falling, and transmits the different motion trajectories of the point falling to the risk assessment unit 4. The risk assessment unit 4 receives the furniture placed in the learning model module 11. When the different motion trajectories of the point falling pass through the placed furniture, it means that the wall debris will hit the placed furniture, and all points passing through the furniture are screened out, as well as the number of recorded points. The damage risk of the wall debris to the furniture is assessed according to the number of points passing through the furniture (that is, the number of wall debris).
[0089] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. The above embodiments and descriptions are only preferred examples of the present invention and are not intended to limit the present invention. Without departing from the spirit and scope of the present invention, the present invention may have various changes and improvements, which fall within the scope of the present invention. The scope of protection of the present invention is defined by the attached claims and their equivalents.
Claims
1. The decoration engineering project risk assessment system based on artificial intelligence is characterized by: It includes a model area unit (1), a vibration assessment unit (2), a data prediction unit (3), a risk assessment unit (4), and a project risk scoring unit (5); The model area unit (1) acquires historical data and establishes a decoration engineering model, the decoration engineering model forms image data of the wall to be demolished, and then discretizes the wall into a plurality of points. When the hammer strikes a plurality of points on the wall surface randomly, the peripheral points spread outward and connect to form a vibration fluctuation area. The vibration assessment unit (2) is used to receive data in the model area unit (1) and calculate the vibration fluctuation distance, and predict the vibration intensity of all hammer strikes superimposed in the vibration fluctuation area based on the data in the model area unit (1) and the vibration fluctuation distance, and then use the superimposed vibration intensity in the vibration fluctuation area and the vibration resistance strength of the tiles to assess the damage risk to the tiles caused by the superimposed vibration intensity in the vibration fluctuation area; The vibration assessment unit (2) comprises a vibration intensity module (21) and a damage assessment module (22); The vibration intensity module (21) is used to receive the hammer force, hammer number, number of covered points, multiple covered points and corresponding coordinates, and historical data from the learning model module (11), receive the points in the intersection area from the fluctuation area module (12), extract pi, density of wall materials, and sound speed data of wall materials from the historical data, and then use the center point of the multiple covered points and the point in the intersection area to calculate the vibration fluctuation distance, and predict the vibration intensity of all hammer superimposed in the vibration fluctuation area based on the hammer force, hammer number, number of covered points, pi, density of wall materials, sound speed of wall materials and vibration fluctuation distance; The damage assessment module (22) is used to receive the superimposed vibration intensity in the vibration fluctuation area in the vibration intensity module (21) and the intersection area in the intersection area module (13), receive the vibration resistance of the tiles in the learning model module (11), and use the superimposed vibration intensity in the vibration fluctuation area and the vibration resistance of the middle tile to evaluate the damage risk to the tiles caused by the superimposed vibration intensity in the vibration fluctuation area. By evaluating the damage risk to the tiles, it is possible to accurately determine which tiles are in a high-risk area. Detailed analysis helps to identify the tiles that are most vulnerable to damage in the vibration fluctuation area, thereby more effectively evaluating potential damage risks. When the superimposed vibration intensity in the vibration fluctuation area is greater than the vibration resistance of the tile, the damage risk of the tile caused by the superimposed vibration intensity in the vibration fluctuation area is evaluated; When the superimposed vibration intensity in the vibration fluctuation area is less than or equal to the vibration resistance of the tile, it is assessed that the superimposed vibration intensity in the vibration fluctuation area does not cause damage risk to the tile; The data prediction unit (3) is used to receive data from the vibration assessment unit (2) and the model area unit (1), regard the wall debris as a number of points in the demolished wall, and predict different movement trajectories of the points falling; The data prediction unit (3) comprises a data recording module (31) and a prediction trajectory module (32); The data recording module (31) is used to receive the predicted superimposed vibration intensity in the vibration intensity module (21) and the vibration resistance of the demolished wall in the learning model module (11). When the predicted superimposed vibration intensity is greater than the vibration resistance of the demolished wall, it means that the demolished wall will be shattered and wall debris will fall. Since the wall is discretized into a number of points and the wall debris is regarded as a number of points in the demolished wall, when the points fall, the corresponding resistance coefficient, point falling speed and falling time, as well as the cross-sectional area of the shattered wall are recorded; The prediction trajectory module (32) is used to receive the resistance coefficient, point drop speed, point drop time and the cross-sectional area of the broken wall in the data recording module (31), receive the historical data in the learning model module (11), extract the gravity acceleration, the mass of the wall material, the air density, the direction of the air resistance and the gravity direction from the historical data, and use the resistance coefficient, point drop speed, point drop time, the cross-sectional area of the broken wall, gravity acceleration, air density and the direction of the air resistance to predict different movement trajectories of the point drop; The risk assessment unit (4) is used to receive data from the data prediction unit (3) and the model area unit (1), and when different motion trajectories of the falling points pass through the placed furniture, all the points passing through the furniture are screened out, and the risk of damage to the furniture caused by the wall debris is assessed according to the number of points passing through the furniture; The project risk scoring unit (5) is used to receive the damage risk to tiles caused by the vibration intensity assessed by the vibration assessment unit (2) and the damage risk to furniture caused by wall debris assessed by the risk assessment unit (4), and to perform risk index scoring for the decoration project.
2. The artificial intelligence decoration engineering project risk assessment system according to claim 1 is characterized by: The model region unit (1) comprises a learning model module (11), a fluctuation region module (12) and an intersection region module (13); The learning model module (11) learns the decoration project through machine learning technology in artificial intelligence, and obtains historical data, and establishes a decoration project model based on the decoration project data and the historical data. The decoration project model forms image data of the wall to be demolished and image data of the environment around the wall, and then uses a discretization algorithm to discretize the wall into a number of points. At the same time, the hammer striking surface is extracted from the decoration project data and randomly hammers multiple points on the wall surface, and then the hammering force and the number of hammering times are recorded. At this time, when the hammer striking surface covers multiple points on the wall surface, vibration fluctuations are generated, and the corresponding coordinates of the covered multiple points and the number of covered points are recorded; The fluctuation area module (12) is used to receive command data for generating vibration fluctuations in the learning model module (11), the fluctuation area module (12) acquires a plurality of covered points from the learning model module (11), and when the plurality of covered points detect the generated vibration fluctuations, the points on the periphery of the coverage diffuse outward along with the vibration fluctuations and connect the diffused periphery points to form a vibration fluctuation area; The intersection area module (13) is used to receive the vibration fluctuation area in the fluctuation area module (12) and the decoration project data in the learning model module (11), extract the decorated tile area around the wall from the decoration project data, and intersect the vibration fluctuation area with the decorated tile area around the wall to obtain the intersection area, and then extract the points that exist in the intersection area and diffuse outward.
3. The artificial intelligence decoration engineering project risk assessment system according to claim 1 is characterized by: The vibration intensity module (21) predicts the vibration intensity of all hammer strikes superimposed in the vibration fluctuation area in accordance with the following principle: Collect hammer strength , hammering times M, number of coverage points , Pi , density of wall materials , the sound velocity of the wall material The vibration intensity of all hammer strikes in the vibration fluctuation area is calculated by calculating the vibration intensity of the superposition of all hammer strikes in the vibration fluctuation area to obtain the superimposed vibration intensity. That is to predict the vibration intensity of all hammer strikes superimposed in the vibration fluctuation area. The specific algorithm formula is: ； in, Refers to the center point to the The square of the distance between the points in the intersection area, Refers to the strength of the i-th hammer blow.
4. The artificial intelligence decoration engineering project risk assessment system according to claim 1 is characterized by: The prediction trajectory module (32) predicts different motion trajectories of the falling point in the following steps: Step 1: Obtain the resistance coefficient , point drop speed , click drop time , the cross-sectional area of the crushed wall , Gravitational acceleration , the quality of wall materials , air density , the direction of air resistance and the direction of gravity. The direction of air resistance is opposite to the direction of velocity. According to the direction of air resistance and velocity, the unit vector of velocity is derived. ; Step 2: Use differential symbols Utilize point drop speed and point drop time Get the acceleration of the point , refers to a vector representing the rate of change of the point velocity; Step 3: Use gravity acceleration , the quality of wall materials and the direction of gravity Gravity ; Step 4: Use air density , drag coefficient , the cross-sectional area of the crushed wall and the unit vector of velocity The air resistance term , the specific algorithm formula is: ； in, is a constant used to adjust the scale of the air resistance formula, It refers to the square of the point drop speed; Step 5: Acceleration of the passing point , Gravity and the air resistance term The different motion trajectories of the calculated point drop are the different motion trajectories of the predicted point drop. The specific algorithm formula is: 。 5. The artificial intelligence decoration engineering project risk assessment system according to claim 1 is characterized by: The risk assessment unit (4) is used to receive different motion trajectories of point drops in the prediction trajectory module (32) and the furniture placed in the decoration project data of the learning model module (11). When the different motion trajectories of the point drops pass through the placed furniture, it means that the wall debris will hit the placed furniture, and all points passing through the furniture are screened out, and the number of points is recorded. The risk of damage to the furniture caused by the wall debris is assessed based on the number of points passing through the furniture.
6. The artificial intelligence decoration engineering project risk assessment system according to claim 5 is characterized by: The project risk scoring unit (5) is used to receive the damage risk of tiles caused by the vibration intensity assessed in the damage assessment module (22) and the damage risk of furniture caused by wall debris assessed in the risk assessment unit (4). The decoration project model scores the risk index of the decoration project according to the assessed damage risk of tiles caused by the vibration intensity and the assessed damage risk of furniture caused by wall debris, and visualizes the score of the risk index.