A multi-objective optimization-based intelligent smoke sensing deployment method

Abstract

The application relates to the technical field of intelligent smoke sensing, and discloses an intelligent smoke sensing deployment method based on multi-target optimization, which has the deployment principle that, under the premise of guaranteeing the accuracy of smoke monitoring and alarm, good performance is achieved in covering monitoring space and smoke monitoring balance with small deployment cost and few deployment nodes. The intelligent smoke sensing deployment method comprises the following steps: S1, constructing a deployment space mathematical model; S2, establishing a smoke sensing coverage radius; S3, calculating the deployment space mathematical model according to multi-target optimization to obtain a smoke sensing deployment position node; the possibility of deployment optimization is improved through regional division of the deployment space, the possibility of a fire point is calculated and judged according to the stored goods in the region, and the smoke sensors are scientifically arranged according to the possibility of a fire, so that the overlapping range of the smoke sensors is reduced, the number of the smoke sensors is reduced, and the monitoring effect of the smoke sensors is effectively guaranteed.

Description

Technical Field

[0001] This invention relates to the field of intelligent smoke detector technology, specifically to an intelligent smoke detector deployment method based on multi-objective optimization. Background Technology

[0002] Smoke detectors are designed to detect large amounts of smoke generated during a fire and promptly issue an alarm. The detectors are controlled by an MCU (Microcontroller Unit) and can intelligently assess smoke levels and trigger an alarm. They are widely used in large, open public spaces such as hotels, shops, internet cafes, lounges, residences, and warehouses.

[0003] However, when deploying smoke detectors in existing tall public spaces, a coverage-style deployment is often used. In this deployment, the detection ranges of the smoke detectors often overlap, resulting in wasted smoke detectors, increased deployment costs, and unnecessary waste. Summary of the Invention

[0004] To address the shortcomings of existing technologies, this invention provides a smart smoke detector deployment method based on multi-objective optimization. This method optimizes smoke detector deployment and effectively reduces the number of smoke detectors while ensuring smoke detection, thereby reducing deployment costs.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a smart smoke detector deployment method based on multi-objective optimization, the deployment principle of which is to achieve good performance in terms of coverage monitoring space and smoke detection balance, while ensuring the accuracy of smoke detection and alarm, with low deployment cost and few deployment nodes. The smart smoke detector deployment method includes the following steps:

[0006] S1. Construct a mathematical model for the deployment space;

[0007] S2. Establish the smoke detector coverage radius;

[0008] S3. Calculate the deployment space mathematical model based on diversified objectives to obtain the smoke detector deployment location nodes, and record the smoke detector location coordinate set as S={CL1,...,CLn}, where CLm is the coordinate of the m-th smoke detector location;

[0009] S4. Divide the deployment space into regions according to diverse objectives; analyze the divided regions to obtain the region set T = {PL1, ..., PLn}, calculate the regional ignition points of the deployment space, where the fire factor value in the PLm region is PCm, and the number of ignition nodes at this location is Rm;

[0010] Construct a deployment space ignition point model:

[0011]

[0012] Where PCj represents the fire factor value of region PLj in region set T, and Rj represents the number of ignition nodes in region PLj in domain set T;

[0013] The number of ignition nodes in the divided area is determined by the ignition point model, and the size and range of the fire after it occurs are judged based on the number of ignition nodes.

[0014] The number of smoke detectors deployed in the PLm area is Cm, and the detection value of each smoke detector in the PLm area is set to Em.

[0015] Construct a deployment space detection value model:

[0016]

[0017] Where Cm is the number of smoke detectors deployed in the PLm area, and Em is the detection value of each smoke detector in the PLm area;

[0018] Build the number of smoke sensor nodes to deploy under the smoke sensor node coverage conditions, and determine the optimal number of deployment nodes.

[0019] Where f1(x) is the spatial ignition point, which represents the probability of a fire occurring within the defined area, and f2(x) is the smoke detection value, representing the monitorable coverage area of ​​the smoke detector within the defined area.

[0020] S5. Perform adaptability calculations on smoke detector deployment nodes;

[0021] S6. Optimize the smoke detector deployment nodes based on the adaptability calculation results;

[0022] S7. Further adjust the positions of the optimized model and the division of the deployment space to obtain the optimal smoke detector deployment node.

[0023] Preferred,

[0024] Preferably, the optimization steps for the smoke detector deployment node are as follows:

[0025] Construct the optimization function:

[0026]

[0027] Wherein, KL and KJ are correction ratio coefficients, PCj represents the fire factor value of region PLj in region set T, Rj represents the number of fire nodes in region PLj in domain set T, Cm is the number of smoke detector nodes deployed in region PLm, and Em is the detection value of each smoke detector node in region PLm.

[0028] ∑ m∈S Cm·Em≥1 indicates that there is at least one smoke detector placement node within the defined area;

[0029] f3(x)≤1, This indicates the minimum number of smoke detection pairs within the defined area.

[0030] Preferably, the optimization of the deployment nodes is to reduce the number of smoke detector nodes in the deployment space while ensuring the best detection effect, so that the number of smoke detector nodes in the divided area is adapted to the ignition point value in the divided area.

[0031] Preferably, the cost of arranging the smoke detector within the deployment space includes the smoke detector cost CA and the additional cost CI for deploying it at its location. The additional cost includes the smoke detector deployment cost and maintenance cost. Therefore, the cost of a smoke detector is CA+CI.

[0032] The deployment cost model is as follows:

[0033]

[0034] Where CAj represents the cost of the smoke detectors deployed in the j-th deployment space, and CIj represents the additional cost of deploying them in the j-th deployment space.

[0035] Based on the deployment cost model, the deployment model with the lowest deployment cost is selected while ensuring the minimum number of smoke detector pairings.

[0036] Preferably, the regional deployment optimization model is as follows:

[0037]

[0038] Where Wi is the multi-objective optimization weight, which is solved using a multi-objective optimization algorithm to find the optimal approximate solution before deploying smoke detection nodes.

[0039] Preferably, when dividing the deployment space into areas, obstacles and turning points within the deployment space, as well as the functionality of the deployment space, are considered. The storage area, aisle area, and office area are divided separately, and the ignition point is estimated based on the types of goods stored in the storage area, the clutter in the aisle area, and the functional nature of the office area.

[0040] Beneficial effects:

[0041] This intelligent smoke detector deployment method based on multi-objective optimization improves the possibility of deployment optimization by dividing the deployment space into regions. It also calculates and judges the possible ignition points based on the goods stored in the region, and scientifically arranges smoke detectors according to the ignition probability, reducing the overlapping range of smoke detectors, reducing the number of smoke detectors, and effectively ensuring the monitoring effect of smoke detectors.

[0042] This intelligent smoke detector deployment method based on multi-objective optimization optimizes smoke detector deployment by calculating the individual cost of smoke detectors and additional deployment costs, and matching these costs with their monitored values, thereby effectively ensuring the scientific nature of multi-objective smoke detector deployment. Detailed Implementation

[0043] The technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0044] Example 1

[0045] A multi-objective optimization-based intelligent smoke detector deployment method is proposed. Its deployment principle is to achieve good performance in terms of coverage area and smoke detection balance, while ensuring accurate smoke detection and alarms, with low deployment cost and few deployment nodes. The intelligent smoke detector deployment method includes the following steps:

[0046] S1. Construct a mathematical model for the deployment space;

[0047] S2. Establish the smoke detector coverage radius;

[0048] S3. Calculate the deployment space mathematical model based on diversified objectives to obtain the smoke detector deployment location nodes, and record the smoke detector location coordinate set as S={CL1,...,CLn}, where CLm is the coordinate of the m-th smoke detector location;

[0049] S4. Divide the deployment space into regions according to diverse objectives;

[0050] The divided regions are analyzed to obtain the region set T = {PL1, ..., PLn}. The regional ignition points of the deployment space are calculated, where the fire factor value in the PLm region is PCm, and the number of ignition nodes at this location is Rm.

[0051] Construct a deployment space ignition point model:

[0052]

[0053] Where PCj represents the fire factor value of region PLj in region set T, and Rj represents the number of ignition nodes in region PLj in domain set T;

[0054] The number of smoke detectors deployed in the PLm area is Cm, and the detection value of each smoke detector in the PLm area is set to Em.

[0055] Construct a deployment space detection value model:

[0056]

[0057] Where Cm is the number of smoke detectors deployed in the PLm area, and Em is the detection value of each smoke detector in the PLm area;

[0058] Where f1(x) is the spatial ignition point, which represents the probability of a fire occurring within the defined area, and f2(x) is the smoke detection value, representing the monitorable coverage area of ​​the smoke detector within the defined area.

[0059] S5. Perform adaptability calculations on smoke detector deployment nodes;

[0060] The specific steps are as follows:

[0061] Construct the optimization function:

[0062]

[0063] Wherein, KL and KJ are correction ratio coefficients, PCj represents the fire factor value of region PLj in region set T, Rj represents the number of fire nodes in region PLj in domain set T, Cm is the number of smoke detector nodes deployed in region PLm, and Em is the detection value of each smoke detector node in region PLm.

[0064] ∑ m∈S Cm·Em≥1 indicates that there is at least one smoke detector placement node within the defined area;

[0065] f3(x)≤1, This indicates the minimum number of smoke detection pairs within the defined area.

[0066] Example 2

[0067] Building upon Example 1, this method adds a parameter for smoke detector deployment cost to further optimize smoke detector node deployment. Specifically, a multi-objective optimization-based intelligent smoke detector deployment method is proposed, with the deployment principle of achieving good performance in terms of coverage area and smoke detection balance while ensuring accurate smoke detection and alarms, with low deployment cost and few deployment nodes.

[0068] The intelligent smoke detector deployment method includes the following steps:

[0069] S1. Construct a mathematical model for the deployment space;

[0070] S2. Establish the smoke detector coverage radius;

[0071] S3. Calculate the deployment space mathematical model based on diversified objectives to obtain the smoke detector deployment location nodes, and record the smoke detector location coordinate set as S={CL1,...,CLn}, where CLm is the coordinate of the m-th smoke detector location;

[0072] S4. Divide the deployment space into regions according to diverse objectives;

[0073] The divided regions are analyzed to obtain the region set T = {PL1, ..., PLn}. The regional ignition points of the deployment space are calculated, where the fire factor value in the PLm region is PCm, and the number of ignition nodes at this location is Rm.

[0074] Construct a deployment space ignition point model:

[0075]

[0076] Where PCj represents the fire factor value of region PLj in region set T, and Rj represents the number of ignition nodes in region PLj in domain set T;

[0077] The number of smoke detectors deployed in the PLm area is Cm, and the detection value of each smoke detector in the PLm area is set to Em.

[0078] Construct a deployment space detection value model:

[0079]

[0080] Where Cm is the number of smoke detectors deployed in the PLm area, and Em is the detection value of each smoke detector in the PLm area;

[0081] Where f1(x) is the spatial ignition point, which represents the probability of a fire occurring within the defined area, and f2(x) is the smoke detection value, representing the monitorable coverage area of ​​the smoke detector within the defined area.

[0082] S5. Perform adaptability calculations on smoke detector deployment nodes;

[0083] The specific steps are as follows:

[0084] Construct the optimization function:

[0085]

[0086] Wherein, KL and KJ are correction ratio coefficients, PCj represents the fire factor value of region PLj in region set T, Rj represents the number of fire nodes in region PLj in domain set T, Cm is the number of smoke detector nodes deployed in region PLm, and Em is the detection value of each smoke detector node in region PLm.

[0087] ∑ m∈S Cm·Em≥1 indicates that there is at least one smoke detector placement node within the defined area;

[0088] f3(x)≤1, This indicates the minimum number of smoke detection pairs within the defined area.

[0089] The cost of arranging the smoke detector within the deployment space includes the cost of the smoke detector CA, and the additional cost CI for deploying it at its location. The additional cost includes the smoke detector deployment cost and maintenance cost. Therefore, the cost of a smoke detector is CA+CI.

[0090] The deployment cost model is as follows:

[0091]

[0092] Where CAj represents the cost of the smoke detectors deployed in the j-th deployment space, and CIj represents the additional cost of deploying them in the j-th deployment space.

[0093] Based on the deployment cost model, the deployment model with the lowest deployment cost is selected while ensuring the minimum number of smoke detector pairings.

[0094] The smoke detector deployment nodes were optimized based on the adaptability calculation results;

[0095] The regional deployment optimization model is as follows:

[0096]

[0097] Where Wi is the multi-objective optimization weight, which is solved using a multi-objective optimization algorithm to find the optimal approximate solution before deploying smoke detection nodes.

[0098] Further positional adjustments were made to the optimized model and the partitioned deployment space to determine the optimal smoke detector deployment node.

[0099] In this embodiment, the optimization of the deployment nodes is to reduce the number of smoke detector nodes in the deployment space while ensuring the best detection effect, so that the number of smoke detector nodes in the divided area is adapted to the ignition point value in the divided area.

[0100] In this embodiment, when dividing the deployment space into areas, obstacles and turning points within the deployment space, as well as the functionality of the deployment space, are considered. The storage area, aisle area, and office area are divided separately, and the ignition point is estimated based on the types of stored goods in the storage area, the clutter in the aisle area, and the functional nature of the office area.

[0101] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A multi-objective optimization based intelligent smoke sensing deployment method, characterized in that, The intelligent smoke detector deployment method includes the following steps: S1. Construct a deployment space mathematical model; S2. Establish the smoke detector coverage radius; S3. Calculate the deployment space mathematical model based on diversified objectives to obtain the smoke detector deployment location nodes, and record the smoke detector location coordinate set as S={CL1,...,CLn}, where CLm is the coordinate of the m-th smoke detector location; S4. Divide the deployment space into regions according to diverse objectives; S5. Perform adaptability calculations on smoke detector deployment nodes; S6. Optimize the smoke detector deployment nodes based on the adaptability calculation results; S7. Further adjust the positions of the optimized model and the division of the deployment space to obtain the optimal smoke detector deployment node; The divided regions are analyzed to obtain the region set T={PL1,...,PLn}. The regional ignition points of the deployment space are calculated, where the fire factor value in the PLm region is PCm, and the number of ignition nodes at this location is Rm. Construct a deployment space ignition point model: Where PCj represents the fire factor value of region PLj in region set T, and Rj represents the number of ignition nodes in region PLj in domain set T; The number of smoke detectors deployed in the PLm area is Cm, and the detection value of each smoke detector in the PLm area is set to Em. Construct a deployment space detection value model: Where Cm is the number of smoke detectors deployed in the PLm area, and Em is the detection value of each smoke detector in the PLm area; wherein, is a space ignition point, the ignition point is a possibility of fire occurring in the divided area space, is a smoke detection value, indicating a monitorable coverage range of smoke in the divided area; The specific steps for optimizing the smoke detector deployment node are as follows: Construct the optimization function: Wherein, KL and KJ are correction ratio coefficients, PCj represents the fire factor value of region PLj in region set T, Rj represents the number of fire nodes in region PLj in domain set T, Cm is the number of smoke detector nodes deployed in region PLm, and Em is the detection value of each smoke detector node in region PLm. ≥ 1, indicating that there is at least one smoke sensing arrangement node in the divided area; ≤1, This indicates the minimum number of smoke detection pairs within the defined area.

2. The intelligent smoke detector deployment method based on multi-objective optimization according to claim 1, characterized in that: The optimization of the deployment nodes aims to reduce the number of smoke detector nodes in the deployment space while ensuring the best detection effect, so that the number of smoke detector nodes in the divided area matches the ignition point value in the divided area.

3. The intelligent smoke detector deployment method based on multi-objective optimization according to claim 1, characterized in that: The cost of arranging the smoke detector within the deployment space includes the cost of the smoke detector CA, and the additional cost CI for deploying it at its location. The additional cost includes the smoke detector deployment cost and maintenance cost. Therefore, the cost of a smoke detector is CA+CI. The deployment cost model is as follows: Where CAj represents the cost of the smoke detectors deployed in the j-th deployment space, and CIj represents the additional cost of deploying them in the j-th deployment space. Based on the deployment cost model, the deployment model with the lowest deployment cost is selected while ensuring the minimum number of smoke detector pairings.

4. The intelligent smoke detector deployment method based on multi-objective optimization according to claim 3, characterized in that: The deployment cost for the defined regions is: = ( ) in To optimize the weights for multiple objectives, a multi-objective optimization algorithm is used to find the optimal approximate solution before deploying smoke detector nodes.

5. The intelligent smoke detector deployment method based on multi-objective optimization according to claim 1, characterized in that: When dividing the deployment space into zones, obstacles and turning points within the deployment space, as well as the functionality of the deployment space, are considered. The storage area, aisle area, and office area are divided separately, and the ignition point is estimated based on the types of goods stored in the storage area, the clutter in the aisle area, and the functional nature of the office area.

Images