Fire monitoring method and device

Abstract

The present invention discloses a fire monitoring method and device, wherein the fire monitoring method obtains the actual smoke signal strength monitored by multiple smoke detectors, compares the measured signal value with the calculated smoke signal strength calculated by using an estimation formula, takes the measured signal value reaching or exceeding the calculated smoke signal strength as the real fire condition, and searches for nodes that meet the fire condition in real time. This method uses the central maximum measured signal value being greater than a certain threshold and the existence of multiple nodes meeting the real fire condition as the judgment basis for fire alarm, which can significantly improve the alarm accuracy of smoke detectors, reduce false alarms, and shorten the alarm time.

Description

Technical Field

[0001] The present invention relates to the field of fire monitoring, and in particular to a fire monitoring method and device. Background Art

[0002] According to the requirements of the national standards "Design Code for Automatic Fire Alarm Systems", "Code for Fire Protection Design of Buildings", "Code for Fire Protection Design of High-rise Civil Buildings" and other standards, all types of buildings are installed with various types of flame detection alarms. However, false alarms, especially false alarms of smoke sensors (smoke detection alarms), have always been a huge problem for the fire protection industry.

[0003] At present, there are several directions for innovation in reducing false alarms and improving the accuracy of fire alarms:

[0004] 1. Improve the quality and sensitivity of the alarm. However, due to the complexity of the installation site, even if the quality of a single alarm is high, the improvement in alarm accuracy is still limited.

[0005] 2. A combination of multiple sensors, such as smoke and temperature sensors. This method has a relatively good effect on reducing false alarms, but it still relies on the quality of a single sensor and cannot obtain the dynamic characteristics of the fire scene, so the improvement is still limited.

[0006] 3. Use machine learning, deep learning and other methods to train multi-sensor prediction models to improve alarm accuracy. However, high-quality fire scene data is difficult to obtain, and the conditions of various fire scenes are ever-changing. The model trained by this method is prone to overfitting, poor generalization ability, and unsatisfactory actual results. Summary of the invention

[0007] In order to solve the above technical problems, the present invention provides a fire monitoring method and device which can improve the alarm accuracy and reduce false alarms.

[0008] In order to achieve the above object, the present invention provides a fire monitoring method, comprising:

[0009] Obtaining actual smoke signal strengths monitored by a plurality of smoke detectors; wherein the plurality of smoke detectors are evenly distributed in the monitoring area;

[0010] When the actual smoke signal strength of one of the smoke detectors reaches the first pre-alarm threshold, it is set as the central node and the signal strength of other smoke detectors is calculated according to the following formula

[0011] S est = K × S0´ (a + bx + cx 2 +dx 3 )

[0012] Among them, a, b, c, and d are empirical parameters, S0 is the actual smoke signal strength of the central node, x is the horizontal distance between the position to be calculated and the central node, and S est is the calculated smoke signal strength at the position to be calculated, K is the scaling factor;

[0013] Determine the actual smoke signal strength and calculated smoke signal strength of all smoke detectors. If the actual smoke signal strength of a smoke detector is greater than or equal to the calculated smoke signal strength, set the smoke detector as the new central node and recalculate the signal strength of other smoke detectors.

[0014] When the actual smoke signal strength of the central node reaches the second pre-alarm threshold, and at least one of all smoke detectors reaches or exceeds the calculated smoke signal strength of the central node, it is determined that the fire has occurred and the alarm is activated.

[0015] Optionally, the empirical parameters are 0.1≤a≤0.2; -0.4 ≤b ≤ -0.3; 0.3 ≤c≤ 0.4; -0.2≤d≤-0.1.

[0016] Optionally, the scaling factor K has a value of 0-1.

[0017] Optionally, the first pre-alarm threshold is 50%-70% of the alarm threshold.

[0018] Optionally, the second pre-alarm threshold is 70%-90% of the alarm threshold.

[0019] Optionally, the smoke detector is deployed in an edge control gateway.

[0020] On the other hand, the present invention also provides a fire monitoring device, comprising:

[0021] An acquisition unit is used to acquire actual smoke signal strengths monitored by a plurality of smoke detectors; wherein the plurality of smoke detectors are evenly distributed in the monitoring area;

[0022] The calculation unit is used to set one of the smoke detectors as the central node when the actual smoke signal strength reaches the first pre-alarm threshold, and calculate the signal strength of other smoke detectors according to the following formula

[0023] S est = K×S0×(a+bx+cx 2 +dx 3 )

[0024] Among them, a, b, c, and d are empirical parameters, S0 is the actual smoke signal strength of the central node, x is the horizontal distance between the position to be calculated and the central node, and S estis the calculated smoke signal strength at the position to be calculated, K is the scaling factor;

[0025] A judgment unit is used to judge the actual smoke signal strength and the calculated smoke signal strength of all smoke detectors. If the actual smoke signal strength of a smoke detector is greater than or equal to the calculated smoke signal strength, the smoke detector is set as a new central node and the signal strengths of other smoke detectors are recalculated;

[0026] The alarm unit is used to determine that a fire has occurred and initiate an alarm when the actual smoke signal strength of the central node reaches a second pre-alarm threshold and at least one of all smoke detectors reaches or exceeds the calculated smoke signal strength of the central node.

[0027] The beneficial effects of the present invention over the prior art are as follows: the fire monitoring method obtains the actual smoke signal strength monitored by multiple smoke detectors, compares the measured smoke signal strength with the estimated smoke signal strength calculated using an estimation formula, takes the measured smoke signal strength reaching or exceeding the calculated smoke signal strength as the real fire condition, and searches for nodes that meet the fire condition in real time. The method uses the central maximum measured signal value being greater than a certain threshold and the existence of multiple nodes meeting the real fire condition as the basis for judging the fire alarm. At the same time, when the smoke signal detected by a single smoke detector rises, the signals detected by other detectors in the detection area can be linked to identify true fire alarms and false alarms by judging whether the signals of each detector meet the overall characteristics of smoke emission during a fire. This can significantly improve the alarm accuracy of smoke detectors, reduce false alarms, and shorten the alarm time. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] Figure 1 It is a flow chart of a fire monitoring method provided by the present invention;

[0029] Figure 2 It is a structural diagram of a fire monitoring device provided by the present invention. DETAILED DESCRIPTION

[0030] 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.

[0031] Reference Figure 1This embodiment provides a fire monitoring method, which is based on a series of smoke detection alarms with remote access functions installed in a building, and an edge control gateway deployed with the fire monitoring method and graph database Neo4j for implementing the fire monitoring method provided in this embodiment.

[0032] S10: Acquire actual smoke signal strengths monitored by a plurality of smoke detectors; wherein the plurality of smoke detectors are evenly distributed in the monitoring area.

[0033] S20: When the actual smoke signal strength of one of the smoke detectors reaches the first pre-alarm threshold, it is set as a central node to calculate the signal strengths of other smoke detectors.

[0034] Specifically, the edge gateway collects the detection signal values ​​of each smoke detector in real time, normalizes them, and stores them in the S attribute of the corresponding node in the graph database. Once a certain S attribute value reaches the first pre-alarm threshold, a warning event is triggered, and the edge gateway starts the alarm algorithm and sets the node (smoke detector) as the central node.

[0035] It should be noted that the first pre-alarm threshold is 50%-70% of the smoke detector alarm threshold. In this embodiment, it is 60% of the smoke detector alarm threshold.

[0036] After the alarm algorithm is started, each time the edge gateway receives data uploaded by the detector, it calculates the signal strength of each other smoke detector based on the signal strength of the central node. The specific calculation formula is as follows:

[0037] S est =K×S0´(a+bx+cx 2 +dx 3 )

[0038] Among them, a, b, c, and d are empirical parameters, S0 is the actual smoke signal strength of the central node, x is the horizontal distance between the position to be calculated and the central node, and S est is the calculated smoke signal strength at the position to be calculated, and K is the scaling factor.

[0039] It should be noted that the values ​​of the empirical parameters a, b, c, and d are as follows: 0.1≤a≤0.2; -0.4≤b≤-0.3; 0.3≤c≤0.4; -0.2≤d≤-0.1. In this embodiment, a is 0.1, b is -0.4, c is 0.3, and d is -0.2.

[0040] S30: Determine the actual smoke signal strength and the calculated smoke signal strength of all smoke detectors. If the actual smoke signal strength of a smoke detector is greater than or equal to the calculated smoke signal strength, set the smoke detector as a new central node and recalculate the signal strengths of other smoke detectors.

[0041] Specifically, all nodes whose actual smoke signal strength is greater than or equal to the calculated smoke signal strength are found through comparison. If there is no node that meets the condition, then determine whether the number of repetitions n is greater than n max , if n>=n max , it is judged as a false alarm and the algorithm process ends. <n max , then wait for the next data refresh to search for nodes that meet the conditions again. If there is a node that meets the conditions, then select the node with the largest signal strength among all nodes that meet the conditions, and record its smoke signal strength as S top , if S top >S0, then this node is used as the new central node, and the new S0= S top , reinitialize the count value n = 0, and repeat the previous step to search for nodes that meet the conditions with the new center node as the center.

[0042] S40: When the actual smoke signal strength of the central node reaches the second pre-alarm threshold, and at least one of all smoke detectors reaches or exceeds the calculated smoke signal strength of the central node, it is determined that the fire has occurred and an alarm is initiated.

[0043] Specifically, when the actual smoke signal strength of the central node reaches the second pre-alarm threshold, if there are still nodes that meet the actual smoke signal strength greater than or equal to the calculated smoke signal strength, it is considered that there is a real fire and an alarm is triggered. If the number of repetitions reaches n max If there is still no node that satisfies the condition that the actual smoke signal strength is greater than or equal to the calculated smoke signal strength, the smoke detector corresponding to the central node is considered to be a false alarm, the alarm algorithm is terminated, and no alarm is given.

[0044] The fire monitoring method obtains the actual smoke signal strength monitored by multiple smoke detectors, compares the measured smoke signal strength with the calculated smoke signal strength calculated using an estimation formula, takes the measured signal value reaching or exceeding the calculated smoke signal strength as the real fire condition, and searches for nodes that meet the fire condition in real time. The method uses the central maximum measured signal value being greater than a certain threshold and the existence of multiple nodes meeting the real fire condition as the basis for judging the fire alarm. At the same time, when the smoke signal detected by a single smoke detector rises, the signals detected by other detectors in the detection area can be linked to identify true fire alarms and false alarms by judging whether the signals of each detector meet the overall characteristics of smoke emission during a fire. This can significantly improve the alarm accuracy of smoke detectors, reduce false alarms, and shorten the alarm time.

[0045] Reference Figure 2 This embodiment also provides a fire monitoring device, including:

[0046] The acquisition unit 100 is used to acquire the actual smoke signal strength monitored by multiple smoke detectors; wherein the multiple smoke detectors are evenly distributed in the monitoring area. It should be noted that since the specific acquisition method and process have been described in detail in step S10 of the above-mentioned fire monitoring method, they will not be repeated here.

[0047] The calculation unit 200 is used to set one of the smoke detectors as the central node when the actual smoke signal strength of the smoke detector reaches the first pre-alarm threshold, and calculate the signal strength of other smoke detectors according to the following formula:

[0048] S est =K×S0×(a+bx+cx 2 +dx 3 )

[0049] Among them, a, b, c, and d are empirical parameters, S0 is the actual smoke signal strength of the central node, x is the horizontal distance between the position to be calculated and the central node, and S est is the calculated smoke signal strength at the position to be calculated, and K is a scaling factor; it should be noted that since the specific technical method and process have been described in detail in step S20 of the above-mentioned fire monitoring method, they will not be repeated here.

[0050] The judgment unit 300 is used to judge the actual smoke signal strength and the calculated smoke signal strength of all smoke detectors. If the actual smoke signal strength of a smoke detector is greater than or equal to the calculated smoke signal strength, the smoke detector is set as a new central node and the signal strengths of other smoke detectors are recalculated. It should be noted that since the specific judgment method and process have been detailed in step S30 of the above-mentioned fire monitoring method, they will not be repeated here.

[0051] The alarm unit 400 is used to determine that a fire has occurred and initiate an alarm when the actual smoke signal strength of the central node reaches a second pre-alarm threshold and at least one of all smoke detectors reaches or exceeds the calculated smoke signal strength of the central node. It should be noted that since the specific alarm method and process have been detailed in step S40 of the above-mentioned fire monitoring method, they will not be repeated here.

[0052] In addition, an embodiment of the present invention further provides a computer-readable storage medium, wherein the computer-readable storage medium may store a program, and when the program is executed, the program includes part or all of the steps of any fire monitoring method recorded in the above method embodiments.

[0053] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0054] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a memory, including several instructions for a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or optical disk and other media that can store program codes.

[0055] A person skilled in the art may understand that all or part of the steps in the various methods of the above embodiments may be completed by instructing related hardware through a program, and the program may be stored in a computer-readable memory, and the memory may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0056] An exemplary flow chart for implementing fire monitoring according to an embodiment of the present invention is described above with reference to the accompanying drawings. It should be noted that the large amount of details included in the above description are only exemplary illustrations of the present invention, rather than limitations of the present invention. In other embodiments of the present invention, the method may have more, fewer or different steps, and the order, inclusion, function, etc. of the steps may be different from those described and illustrated.

Claims

1. A fire monitoring method, characterized in that: include: Obtaining actual smoke signal strength monitored by multiple smoke detectors; wherein the plurality of smoke detectors are evenly distributed within the monitoring area; When the actual smoke signal strength of one of the smoke detectors reaches the first pre-alarm threshold, it is set as the central node and the signal strength of other smoke detectors is calculated according to the following formula S est = K×S0×(a + bx + cx 2 +dx 3 ) Among them, a, b, c, and d are empirical parameters, S0 is the actual smoke signal strength of the central node, x is the horizontal distance between the position to be calculated and the central node, and S est is the calculated smoke signal strength at the position to be calculated, K is the scaling factor; Determine the actual smoke signal strength and calculated smoke signal strength of all smoke detectors. If the actual smoke signal strength of a smoke detector is greater than or equal to the calculated smoke signal strength, set the smoke detector as the new center node and recalculate the signal strength of other smoke detectors. If there is a node that meets the conditions, select the node with the largest signal strength from all nodes that meet the conditions, and record its smoke signal strength as S. top , if S top > S0, then this node is used as the new central node, and the new S0 = S top ; When the actual smoke signal strength of the central node reaches the second pre-alarm threshold, and at least one of all smoke detectors reaches or exceeds the calculated smoke signal strength of the central node, it is determined that the fire has occurred and the alarm is activated.

2. The fire monitoring method according to claim 1, characterized in that: The empirical parameters are 0.1≤a≤0.2; -0.4≤b ≤ -0.3; 0.3 ≤c≤ 0.4; -0.2≤d≤-0.

1.

3. The fire monitoring method according to claim 1, characterized in that: The scaling factor K ranges from 0 to 1.

4. The fire monitoring method according to claim 1, characterized in that: The first pre-alarm threshold is 50%-70% of the alarm threshold.

5. The fire monitoring method according to claim 1, characterized in that: The second pre-alarm threshold is 70%-90% of the alarm threshold.

6. The fire monitoring method according to claim 1, characterized in that: The smoke detector is deployed in the edge control gateway.

7. A fire monitoring device, characterized in that: include: An acquisition unit, used for acquiring actual smoke signal strengths monitored by a plurality of smoke detectors; wherein the plurality of smoke detectors are evenly distributed within the monitoring area; The calculation unit is used to set one of the smoke detectors as the central node when the actual smoke signal strength reaches the first pre-alarm threshold, and calculate the signal strength of other smoke detectors according to the following formula S est = K×S0×(a + bx + cx 2 +dx 3 ) Among them, a, b, c, and d are empirical parameters, S0 is the actual smoke signal strength of the central node, x is the horizontal distance between the position to be calculated and the central node, and S est is the calculated smoke signal strength at the position to be calculated, K is the scaling factor; The judgment unit is used to judge the actual smoke signal strength of all smoke detectors and the calculated smoke signal strength. If the actual smoke signal strength of a smoke detector is greater than or equal to the calculated smoke signal strength, the smoke detector is set as the new central node and the signal strengths of other smoke detectors are recalculated; if there is a node that meets the conditions, the node with the largest signal strength is selected from all nodes that meet the conditions, and its smoke signal strength is recorded as S top , if S top > S0, then this node is used as the new central node, and the new S0 = S top ; The alarm unit is used to determine that a fire has occurred and initiate an alarm when the actual smoke signal strength of the central node reaches a second pre-alarm threshold and at least one of all smoke detectors reaches or exceeds the calculated smoke signal strength of the central node.

8. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of a fire monitoring method according to any one of claims 1 to 6 are implemented.

Images