Evaluation system for fire rescue rope system

Abstract

The invention relates to the technical field of fire rescue ropes, and particularly discloses a fire rescue rope system evaluation system, which comprises a video acquisition module, an augmented reality output screen module, an anchor point analysis module and a system stress evaluation module, the system can automatically evaluate the strength of different types of anchor points including tree, steel structure and rock anchor points, the maximum stress range of the anchor points is accurately calculated, it is ensured that the anchor points do not lose efficacy in the rescue process, and therefore the safety of the whole system is improved, the system can automatically detect whether a rope system conforms to the double-rope backup principle or not, and the safety of the system is improved. It is ensured that when any rope fails, the standby rope can immediately bear loads and prevent personnel from falling down, the evaluation system can ensure that when all operators suddenly lose consciousness at any moment, the system can still maintain the safety of the operators and prevent accidents, and the system can automatically recognize and analyze whether the rope system is built correctly or not; and tedious and time-consuming manual inspection is avoided.

Description

Technical Field

[0001] The invention belongs to the technical field of fire rescue ropes, and in particular relates to a fire rescue rope system evaluation system. Background Art

[0002] In the field of fire rescue, the rope system is an important rescue tool, and its safety and reliability are directly related to the success of the rescue operation and the life safety of the rescuers. Traditional rope system evaluation mainly relies on the experience and intuition of rescuers. This evaluation method is not only inefficient, but also has the risk of missing key safety risks.

[0003] In order to solve these problems, in recent years, with the advancement of science and technology and the development of intelligent technology, the fire rescue rope system evaluation system has gradually become a hot spot for research and application. This type of system can quickly and accurately determine the safety and reliability of the rope system through automatic detection and evaluation of the rope system, thereby improving the efficiency and safety of the rescue operation.

[0004] Specifically, the fire rescue rope assessment system uses a variety of advanced technical means, including sensor technology, data analysis technology, image recognition technology, etc. Through the sensors installed on the rope system, the system can monitor the status of the rope system in real time, including the tension, angle, length and other parameters of the rope. At the same time, the system can also automatically identify the strength of the anchor points in the system, whether they meet the safety standards, and whether they meet the safety requirements such as "sudden death" (i.e. instant failure) and the double rope backup principle.

[0005] In addition, the system can automatically calculate the maximum force range of the rope system and identify the weakest link in the system through a built-in algorithm. Once a potential safety risk is found, the system can immediately warn rescuers and provide corresponding risk warnings and suggestions.

[0006] In short, the emergence of the fire rescue rope system evaluation system has brought revolutionary changes to the field of fire rescue. It can not only improve the efficiency and safety of rescue operations, but also reduce the risks and workload of rescuers. With the continuous development and improvement of technology, it is believed that such systems will play an increasingly important role in future fire rescue.

[0007] In view of this, the inventor proposes a fire rescue rope system evaluation system to solve the above problems. Summary of the invention

[0008] The object of the present invention is to provide a fire rescue rope system evaluation system to solve the problems raised in the above background technology.

[0009] To achieve the above object, the present invention provides the following technical solutions:

[0010] Fire rescue rope system assessment system, including:

[0011] The video acquisition module includes a high-resolution camera, an image processing unit, and an angle measurement sensor, providing real-time video monitoring, with angle measurement, knot recognition, and equipment recognition functions, and acquiring video image data;

[0012] The augmented reality output screen module simulates the on-site environment and shows what the equipment will look like after it is successfully built. The high-resolution display screen and augmented reality software are used to simulate the on-site environment and equipment location and obtain environmental and location data.

[0013] Anchor point analysis module, which analyzes the maximum force range of common anchor points and obtains common anchor point data. Common anchor points include trees, steel structures and boulders.

[0014] The system force assessment module uses machine learning technology to analyze video data, environmental and location data, and common anchor point data, optimize the system assessment model, analyze the system's force points, and identify the system's force state. It includes a double rope system selection unit, a sudden death principle detection unit, an equipment force range identification unit, and a system maximum force analysis unit.

[0015] Preferably, common anchor point analysis includes:

[0016] Trees: Identify the thickness and type of trees and estimate their maximum stress value;

[0017] Steel structure: evaluate the maximum load range according to type and thickness;

[0018] Boulders: Estimate the maximum force on the boulder by its size.

[0019] Preferably, the double rope system selection unit is used to confirm whether there is a backup system at each point, and to give a prompt if there is a deficiency, including:

[0020] Double rope and double main lock protection: ensure that every key point in the system has double protection;

[0021] Pulley broken shaft protection: Each pulley must have broken shaft protection;

[0022] Non-forced systems: Lateral migration systems do not require double protection.

[0023] Preferably, the sudden death principle detection unit ensures that when the operator suddenly loses consciousness, the system does not cause a person to fall or fail;

[0024] Real-time monitoring: to ensure that the system does not fail when the hands are released;

[0025] Safety assurance: After the system is set up, personnel are only responsible for operation and no longer need to worry about safety.

[0026] Preferably, the equipment force range identification unit automatically identifies the force range and rope diameter range of the equipment, determines whether there is an unreasonable position in the system, and performs risk assessment;

[0027] System inspection: conduct a comprehensive inspection of the security of the entire system;

[0028] Risk assessment: Automatically identify and alert potential security risks.

[0029] Preferably, the system maximum force analysis unit includes bottleneck identification and maximum bearing capacity calculation. The bottleneck identification determines the bottleneck position of the force in the system, and the maximum bearing capacity calculation calculates the maximum rescue bearing capacity of the system.

[0030] Preferably, the machine learning technology is specifically:

[0031] S1. Collect sensor data: collect angle measurement, knot recognition, equipment recognition sensor data, equipment parameters: maximum load and wear data of various ropes, pulleys, anchor equipment;

[0032] S2. Preprocess the data, including: cleaning, removing noise data and outliers; data normalization, normalizing data of different dimensions; feature extraction, extracting important features, including rope force and anchor strength;

[0033] S3. Use the preprocessed data to train models, including regression model prediction, classification model, and clustering model;

[0034] S4. Real-time evaluation, real-time data input: Input the real-time data collected on site into the model for evaluation, including:

[0035] Safety load prediction: predict the maximum force and safety load of the rope system through regression model;

[0036] Safety standard detection: Use classification models to detect whether the system complies with safety standards;

[0037] Risk warning: Identify potential risks and abnormal situations through clustering models and give warnings.

[0038] Preferably, the regression model is used to predict the maximum force and the safety load, expressed as:

[0039] F max =w T x+b

[0040] Among them, F max： Predicted maximum force;

[0041] W: model weight vector;

[0042] x: feature vector, including rope diameter, angle, and anchor type;

[0043] b: Bias term.

[0044] Preferably, the classification model is used to detect safety standards, including the double rope backup principle and the sudden death principle, which are expressed as:

[0045]

[0046] Where P(y|x): the probability that the system meets the safety standards;

[0047] w: model weight vector;

[0048] x: eigenvector;

[0049] b: Bias term.

[0050] Preferably, the clustering model is used to discover patterns and anomalies in different rescue scenarios, expressed as:

[0051]

[0052] Where C: cluster center set;

[0053] n: number of clusters;

[0054] x: data point;

[0055] μ i： The i-th cluster center.

[0056] Compared with the prior art, the present invention has the following beneficial effects:

[0057] (1) The system of the present invention can automatically evaluate the strength of different types of anchor points, including tree, steel structure and boulder anchor points, etc., and accurately calculate the maximum force range of the anchor point to ensure that the anchor point will not fail during the rescue process, thereby improving the safety of the overall system. The system can automatically detect whether the rope system complies with the double-rope backup principle to ensure that when any rope fails, the backup rope can immediately bear the load to prevent people from falling.

[0058] (2) The evaluation system of the present invention ensures that when all operators suddenly lose consciousness at any time, the system can still maintain the safety of the personnel and prevent accidents. The system can automatically identify and analyze whether the rope system is built correctly, avoiding the tedious and time-consuming manual inspection and speeding up the construction process of the rescue system. The system can monitor the stress conditions of the ropes and anchor points in real time, automatically prompt potential risks and the weakest links of the system, help rescue personnel make quick adjustments, and improve rescue efficiency.

[0059] (3) The present invention reduces the possibility of human calculation errors by automatically calculating the maximum force range and safe load of the rope system. The system can analyze based on real-time data to provide more accurate and reliable evaluation results. The system can automatically identify the type and parameters of the equipment used (such as maximum load, rope diameter, etc.) to ensure that all equipment is used within a reasonable force range, reducing safety hazards caused by improper equipment selection. BRIEF DESCRIPTION OF THE DRAWINGS

[0060] Figure 1 It is a block diagram of the fire rescue rope system evaluation system of the present invention;

[0061] Figure 2 The flowchart of the machine learning technology of the present invention is shown in FIG. DETAILED DESCRIPTION

[0062] The following will be combined with the drawings in the embodiments of 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.

[0063] Embodiment 1:

[0064] See also Figure 1 to Figure 2 As shown, the fire rescue rope system evaluation system includes:

[0065] The video acquisition module includes a high-resolution camera, an image processing unit, and an angle measurement sensor, providing real-time video monitoring, with angle measurement, knot recognition, and equipment recognition functions, and acquiring video image data;

[0066] The augmented reality output screen module simulates the on-site environment and shows what the equipment will look like after it is successfully built. The high-resolution display screen and augmented reality software are used to simulate the on-site environment and equipment location and obtain environmental and location data.

[0067] Anchor point analysis module, which analyzes the maximum force range of common anchor points and obtains common anchor point data. Common anchor points include trees, steel structures and boulders.

[0068] The system force assessment module uses machine learning technology to analyze video data, environmental and location data, and common anchor point data, optimize the system assessment model, analyze the system's force points, and identify the system's force state. It includes a double rope system selection unit, a sudden death principle detection unit, an equipment force range identification unit, and a system maximum force analysis unit.

[0069] Specifically, common anchor point analysis includes:

[0070] Trees: Identify the thickness and type of trees and estimate their maximum stress value;

[0071] Steel structure: evaluate the maximum load range according to type and thickness;

[0072] Boulders: Estimate the maximum force on the boulder by its size.

[0073] Specifically, the double rope system selection unit is used to confirm whether there is a backup system at each point, and give a prompt if there is a deficiency, including:

[0074] Double rope and double main lock protection: ensure that every key point in the system has double protection;

[0075] Pulley broken shaft protection: Each pulley must have broken shaft protection;

[0076] Non-forced systems: Lateral migration systems do not require double protection.

[0077] Specifically, the sudden death principle detection unit ensures that when the operator suddenly loses consciousness, the system does not cause a person to fall or fail;

[0078] Real-time monitoring: to ensure that the system does not fail when the hands are released;

[0079] Safety assurance: After the system is set up, personnel are only responsible for operation and no longer need to worry about safety.

[0080] Specifically, the equipment force range identification unit automatically identifies the force range and rope diameter range of the equipment, determines whether there is an unreasonable position in the system, and performs risk assessment;

[0081] System inspection: conduct a comprehensive inspection of the security of the entire system;

[0082] Risk assessment: Automatically identify and alert potential security risks.

[0083] Specifically, the system maximum force analysis unit includes bottleneck identification and maximum bearing capacity calculation. The bottleneck identification determines the bottleneck position of the force in the system, and the maximum bearing capacity calculation calculates the maximum rescue bearing capacity of the system.

[0084] Specifically, the machine learning technology is:

[0085] S1. Collect sensor data: collect angle measurement, knot recognition, equipment recognition sensor data, equipment parameters: maximum load and wear data of various ropes, pulleys, anchor equipment;

[0086] S2. Preprocess the data, including: cleaning, removing noise data and outliers; data normalization, normalizing data of different dimensions; feature extraction, extracting important features, including rope force and anchor strength;

[0087] S3. Use the preprocessed data to train models, including regression model prediction, classification model, and clustering model;

[0088] S4. Real-time evaluation, real-time data input: Input the real-time data collected on site into the model for evaluation, including:

[0089] Safety load prediction: predict the maximum force and safety load of the rope system through regression model;

[0090] Safety standard detection: Use classification models to detect whether the system complies with safety standards;

[0091] Risk warning: Identify potential risks and abnormal situations through clustering models and give warnings.

[0092] Specifically, the regression model is used to predict the maximum force and safety load, which is expressed as:

[0093] F max =w T x+b

[0094] Among them, F max： Predicted maximum force;

[0095] W: model weight vector;

[0096] x: feature vector, including rope diameter, angle, and anchor type;

[0097] b: Bias term.

[0098] Specifically, the classification model is used to detect safety standards, including the double rope backup principle and the sudden death principle, which are expressed as:

[0099]

[0100] Where P(y|x): the probability that the system meets the safety standards;

[0101] w: model weight vector;

[0102] x: eigenvector;

[0103] b: Bias term.

[0104] Specifically, the clustering model is used to discover patterns and anomalies in different rescue scenarios, which can be expressed as:

[0105]

[0106] Where C: cluster center set;

[0107] n: number of clusters;

[0108] x: data point;

[0109] μ i： The i-th cluster center.

[0110] In a rescue mission, the maximum force and safety of the system need to be evaluated in real time, as follows:

[0111] Collect data:

[0112] Tree diameter d = 0.5 m;

[0113] Rope diameter r = 0.04 m;

[0114] Anchor type tree;

[0115] Other relevant features;

[0116] Eigenvectors:

[0117] x=[0.5,0.04,tree]

[0118] The regression model predicts the maximum force:

[0119] According to the trained model parameters w and b, w = [1.5, 0.8], b = 2.0, the predicted maximum force value is obtained:

[0120] F max =[1.5,0.8]·[0.5,0.04,"tree"]+2.0

[0121] Classification model detection safety standards:

[0122]

[0123] Calculate the probability that the system meets the safety standards, and train the model parameters w and b, w = [2.0, -1.5], b = -0.5;

[0124]

[0125] Among them, P(y|x)>0.5, indicating that the system meets the safety standards.

[0126] A rescue system consists of the following parameters:

[0127] Tree anchor point, diameter d = 0.5m;

[0128] Rope diameter rd = 0.04m;

[0129] Tensile strength σr = 1000 MPa;

[0130] Pulley, tensile strength σp = 500MPa;

[0131] Cross-sectional area Ap = 0.001 m 2 ;

[0132] The knot efficiency coefficient η = 0.8;

[0133] Safety factor SF = 5;

[0134] Calculate the maximum bearing capacity of the tree anchor point:

[0135] F tree = k·d 2 =150·0.5 2 =37.5kN

[0136] (where k = 150KN)

[0137] Calculate the maximum load-bearing capacity of the rope:

[0138]

[0139] Calculate the maximum load capacity of the pulley:

[0140] Fp=σp·Ap=500·0.01=5kN

[0141] Calculate the maximum load-bearing capacity of the knot:

[0142] Fk=η·Fr=0.8*25.13=20.1kN

[0143] Determine the maximum load capacity of the system:

[0144] Fs=min(Fr,Fp,Fk)=min(37.5,25.13,5.20.1)=5kN

[0145] Determine the maximum rescue range:

[0146] Max Load=min(Ftree,Fs)=min(37.5,5)=5kN

[0147] In this system, the maximum rescue load of the entire system is 5kN, which is determined by the maximum load-bearing capacity of the pulley. Therefore, in actual operation, ensure that the rescue system operates within a load range not exceeding 5kN to ensure safety.

[0148] As can be seen from the above, the system of the present invention can automatically evaluate the strength of different types of anchor points, including tree, steel structure and boulder anchor points, etc., and ensure that the anchor points will not fail during the rescue process by accurately calculating the maximum force range of the anchor points, thereby improving the safety of the overall system. The system can automatically detect whether the rope system complies with the double-rope backup principle, ensuring that when any rope fails, the spare rope can immediately bear the load to prevent people from falling.

[0149] The evaluation system ensures that all operators can maintain their safety and prevent accidents when they suddenly lose consciousness at any time. The system can automatically identify and analyze whether the rope system is built correctly, avoiding the tedious and time-consuming manual inspection and speeding up the process of building the rescue system. The system can monitor the stress of ropes and anchor points in real time, automatically prompt potential risks and the weakest links of the system, help rescuers make quick adjustments, and improve rescue efficiency.

[0150] By automatically calculating the maximum force range and safe load of the rope system, the possibility of human calculation errors is reduced. The system can analyze based on real-time data to provide more accurate and reliable evaluation results. The system can automatically identify the type and parameters of the equipment used (such as maximum load, rope diameter, etc.) to ensure that all equipment is used within a reasonable force range and reduce safety hazards caused by improper equipment selection.

[0151] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine different embodiments or examples described in this specification and the features of different embodiments or examples, unless they are contradictory.

[0152] In the drawings of the embodiments disclosed in the present invention, only the structures related to the embodiments disclosed in the present invention are involved, and other structures can refer to the general design. In the absence of conflict, the same embodiment and different embodiments of the present invention can be combined with each other.

[0153] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. Fire rescue rope system evaluation system, characterized in that, include: The video acquisition module includes a high-resolution camera, an image processing unit, and an angle measurement sensor, providing real-time video monitoring, with angle measurement, knot recognition, and equipment recognition functions, and acquiring video image data; The augmented reality output screen module simulates the on-site environment and shows what the equipment will look like after it is successfully built. The high-resolution display screen and augmented reality software are used to simulate the on-site environment and equipment location and obtain environmental and location data. Anchor point analysis module, which analyzes the maximum force range of common anchor points and obtains common anchor point data. Common anchor points include trees, steel structures and boulders. The system force assessment module uses machine learning technology to analyze video data, environmental and location data, and common anchor point data, optimize the system assessment model, analyze the system's force points, and identify the system's force state. It includes a double rope system selection unit, a sudden death principle detection unit, an equipment force range identification unit, and a system maximum force analysis unit.

2. The fire rescue rope system evaluation system according to claim 1, characterized in that: Common anchor point analyses include: Trees: Identify the thickness and type of trees and estimate their maximum stress value; Steel structure: evaluate the maximum load range according to type and thickness; Boulders: Estimate the maximum force on the boulder by its size.

3. The fire rescue rope system evaluation system according to claim 1, characterized in that: The double rope system selection unit is used to confirm whether there is a backup system at each point, and give a prompt if there is a deficiency, including: Double rope and double main lock protection: ensure that every key point in the system has double protection; Pulley broken shaft protection: Each pulley must have broken shaft protection; Non-forced systems: Lateral migration systems do not require double protection.

4. The fire rescue rope system evaluation system according to claim 1, characterized in that: The sudden death principle detection unit ensures that when the operator suddenly loses consciousness, the system does not cause a person to fall or fail; Real-time monitoring: to ensure that the system does not fail when the hands are released; Safety assurance: After the system is set up, personnel are only responsible for operation and no longer need to worry about safety.

5. The fire rescue rope system evaluation system according to claim 1, characterized in that: The equipment force range identification unit automatically identifies the force range and rope diameter range of the equipment, determines whether there is an unreasonable position in the system, and performs risk assessment; System inspection: conduct a comprehensive inspection of the security of the entire system; Risk assessment: Automatically identify and alert potential security risks.

6. The fire rescue rope system evaluation system according to claim 1, characterized in that: The system maximum force analysis unit includes bottleneck identification and maximum bearing capacity calculation. The bottleneck identification determines the bottleneck position of the force in the system, and the maximum bearing capacity calculation calculates the maximum rescue bearing capacity of the system.

7. The fire rescue rope system evaluation system according to claim 1, characterized in that: The machine learning technology is specifically: S1. Collect sensor data: collect angle measurement, knot recognition, equipment recognition sensor data, equipment parameters: maximum load and wear data of various ropes, pulleys, anchor equipment; S2. Preprocess the data, including: cleaning, removing noise data and outliers; data normalization, normalizing data of different dimensions; feature extraction, extracting important features, including rope force and anchor strength; S3. Use the preprocessed data to train models, including regression model prediction, classification model, and clustering model; S4. Real-time evaluation, real-time data input: Input the real-time data collected on site into the model for evaluation, including: Safety load prediction: predict the maximum force and safety load of the rope system through regression model; Safety standard detection: Use classification models to detect whether the system complies with safety standards; Risk warning: Identify potential risks and abnormal situations through clustering models and give warnings.

8. The fire rescue rope system evaluation system according to claim 7, characterized in that: The regression model is used to predict the maximum force and safety load, expressed as: F max =w T x+b where F max： Predicted maximum force; W: model weight vector; x: feature vector, including rope diameter, angle, and anchor type; b: Bias term.

9. The fire rescue rope system evaluation system according to claim 7, characterized in that: The classification model is used to detect safety standards, including the double rope backup principle and the sudden death principle, which is expressed as: Where P(y|x): the probability that the system meets the safety standards; w: model weight vector; x: eigenvector; b: Bias term.

10. The fire rescue rope system evaluation system according to claim 7, characterized in that: The clustering model is used to discover patterns and anomalies in different rescue scenarios, expressed as: Where C: cluster center set; n: number of clusters; x: data point; μ i： The i-th cluster center.

Images