An elevator car fire warning device and an automatic fire extinguishing device

Abstract

An elevator car fire warning device and an automatic fire extinguishing device belong to the technical field of fire warning. The elevator car fire warning device includes a detection unit and a first control unit. The detection unit includes a sensor array; the first control unit includes a fire element recognition model and a fire recognition model. The fire element recognition model obtains K fire element data according to the information provided by the sensor array; the fire recognition model estimates the probability of a fire according to the K fire element quantization data provided by the fire element recognition model, and the fire recognition model is trained by a probability model. The fire recognition model of the elevator car fire warning device provided by the present invention has good generalization ability.

Description

Technical Field

[0001] The present invention relates to an elevator car fire warning device and an automatic fire extinguishing device, belonging to the technical field of fire warning. Background Art

[0002] For example, a Chinese invention patent application with the publication number CN115771823A discloses an elevator fire emergency treatment and alarm system, which is applied in a vertically lifting elevator. The elevator moves up and down in a corresponding elevator shaft. The fire emergency treatment and alarm system includes a smoke alarm, a sprinkler mechanism, and a liquid storage mechanism. The smoke alarm is arranged on the upper inner wall of the elevator, the sprinkler mechanism is arranged inside the elevator, and the liquid storage mechanism includes a liquid storage tank. The liquid storage tank stores a fire extinguishing agent for fire extinguishing. One side of the liquid storage tank is provided with a fire extinguishing pipe for delivering the fire extinguishing agent into the sprinkler mechanism. The design of the smoke alarm can use sensors to timely detect the occurrence of a fire inside the elevator, and then transmit it to the control system through the smoke alarm, and give an alarm in time through the control system. And through the control system, the liquid storage mechanism and the sprinkler mechanism are controlled to perform timely sprinkler fire extinguishing emergency treatment on the inside of the elevator, thereby realizing the emergency treatment of elevator fires and being able to extinguish fires and give alarms in time.

[0003] However, only a smoke alarm is set inside the elevator, and only when a fire occurs can the smoke be sensed. At this time, if the elevator is between safety exits, the fire will spread rapidly and cause harm to people. Summary of the Invention

[0004] To overcome the shortcomings in the prior art, the present invention provides an elevator car fire warning device and an automatic fire extinguishing device, which obtain K fire elements through a fire element recognition model according to the information provided by a sensor array; estimate the probability of a fire occurring through the quantification data of the K fire elements provided by the fire recognition model. It can prevent problems before they occur, and the fire recognition model is trained through a probability model. Through the training method of the present invention, the fire recognition model can have good generalization ability.

[0005] To achieve the above-mentioned invention purpose, on the one hand, the present invention provides an elevator car fire warning device, which includes a detection unit and a first control unit. The detection unit includes a sensor array; the first control unit includes a fire element recognition model and a fire recognition model. The fire element recognition model obtains K fire elements according to the information provided by the sensor array; the fire recognition model estimates the probability of a fire occurring according to the quantification data of the K fire elements provided by the fire element recognition model. The fire recognition model is trained through a probability model, and the process includes:

[0006] S1-1: Obtain a series of past fire element quantification data of the elevator car to form a data vector , where \(n\) is a positive integer greater than or equal to 2; \(K\) is a positive integer greater than or equal to 2;

[0007] S1-2: Construct a probability model \(p\) of a fire occurring:

[0008] ,

[0009] where, , represents a scalar function of the quantification data of the \(k\)-th fire element , and is a parameter;

[0010] S1-3: Estimate the optimal parameter of: :

[0011] ,

[0012] where, is the likelihood function, and its gradient is:

[0013] ;

[0014] , represents the gradient of , represents the expectation of ; represents the expectation of ;;

[0015] S1-4: Obtain a set of positive samples from the data vector , where \(m\) is a positive integer less than or equal to \(n\); Obtain a set of negative samples according to the following formula:

[0016] ,

[0017] where, is a set coefficient, is a transformation relationship;

[0018] S1-5: Update through the following formula:

[0019] ,

[0020] where, is the learning coefficient;

[0021] S1-6: Obtain a fire recognition model based on the updated :

[0022] 。

[0023] To achieve the above-mentioned invention purpose, the present invention further provides an automatic fire extinguishing device, which includes a second control unit, a motor driver, an exhaust fan driver and a second communication unit. The second communication unit is used for communicating and connecting with the above-mentioned elevator car fire early warning device. When the second control unit receives a detection instruction through the second communication unit, the second control unit provides an instruction to the motor driver, and the motor driver controls the motor to drive the emergency air inlet and smoke exhaust port mechanism to operate to open the emergency air inlet and smoke exhaust port. After running for a set time, the emergency air inlet and smoke exhaust port are then closed; the second control unit provides an instruction to the exhaust fan driver, and the exhaust fan driver controls the exhaust fan to run. After running for a set time, the exhaust fan then stops running.

[0024] Compared with the prior art, an elevator car fire early warning device and an automatic fire extinguishing device provided by the present invention have the following beneficial effects:

[0025] The present invention obtains K fire elements through a fire element recognition model according to the information provided by a sensor array; estimates the probability of a fire through the quantization data of the K fire elements provided by the fire recognition model (the fire element recognition model). It can prevent problems before they occur, and the fire recognition model is trained through a probability model. Through the training method of the present invention, the fire recognition model can have good generalization ability. Description of the Drawings

[0026] Figure 1 is a block diagram of the elevator car fire early warning device provided by the present invention.

[0027] Figure 2 is a block diagram of the fire element recognition model provided by the present invention.

[0028] Figure 3 is a block diagram of the automatic fire extinguishing device provided by the present invention. Detailed Embodiments

[0029] In order to make the technical problems, technical solutions and beneficial effects to be solved by the present invention clearer, the present invention will be further described in detail below with reference to the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0030] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, features defined with "first" and "second" may explicitly or implicitly include one or more of such features. In the description of the present invention, "a plurality of" means two or more, unless otherwise specifically defined. "Several" means one or more, unless otherwise specifically defined.

[0031] Figure 1 is the block diagram of the elevator car fire warning device provided in the first embodiment of the present invention. As Figure 1 shown, an elevator car fire warning device provided by the present invention includes a detection unit and a first control unit. The detection unit includes a sensor array; the first control unit includes a fire element recognition model and a fire recognition model. The fire element recognition model obtains K fire elements according to the information provided by the sensor array; the fire recognition model estimates the probability of a fire occurring according to the quantization data of the K fire elements provided by the fire element recognition model. In the present invention, the sensor array at least includes an image sensor.

[0032] In the present invention, the fire recognition model is trained by a probability model, and the process includes:

[0033] S1-1: Obtain a series of quantization data of fire elements in the past of the elevator car to form a data vector , where n is a positive integer greater than or equal to 2; K is a positive integer greater than or equal to 2;

[0034] S1-2: Construct a probability model p of a fire occurring:

[0035] ,

[0036] In the formula, , represents a scalar function with respect to the quantization data of the k-th fire element, is a parameter;

[0037] S1-3: Estimate the optimal parameter of : ,

[0038] In the formula, is the likelihood function, and its gradient is:

[0039] ;

[0040] , represents the derivative of The gradient of represents the expectation of ; represents the expectation of ;;

[0041] S1-4: Obtain a set of positive samples from the data vector , where m is a positive integer less than or equal to n; obtain a set of negative samples according to the following formula :

[0042] ,

[0043] In the formula, is the set coefficient, is the transformation relationship;

[0044] S1-5: Update through the following formula:

[0045] ,

[0046] In the formula, is the learning coefficient;

[0047] S1-6: Obtain the fire recognition model according to the updated :

[0048] .

[0049] In the present invention, ,

[0050] In the formula, represents the divergence, represents the changing space; represents when the distribution of is the empirical distribution of

[0051] In the present invention, the elevator car fire warning device further includes an audible and visual alarm. The first control unit causes the audible and visual alarm to display a light signal corresponding to the probability value of a fire occurring and emit a sound signal corresponding to the probability value of a fire occurring.

[0052] In the present invention, the elevator car fire warning device further includes a first communication unit. When the probability of a fire occurring is greater than or equal to a first threshold, the first control unit sends a detection instruction to the automatic fire extinguisher through the first communication unit to detect whether the smoke exhaust module is in good condition; at the same time, it sends a warning message to the host computer. The smoke exhaust module includes a motor driver and an emergency air inlet and smoke outlet mechanism.

[0053] In the present invention, when the probability of a fire occurring is greater than or equal to a second threshold, the first control unit sends a fire extinguishing and smoke exhaust instruction to the automatic fire extinguisher, and at the same time sends elevator car fire extinguishing and smoke exhaust information to the host computer, and the second threshold is greater than the first threshold.

[0054] In the present invention, the elevator car fire warning device further includes a first storage unit for storing a control program and data. The control program includes a program for processing signals obtained by the sensor array and controlling the actions of the sound and light alarm and the first communication unit according to the processing results.

[0055] Figure 2 is a block diagram of the composition of the fire element recognition model provided by the present invention, as Figure 2 shown, the fire element recognition model is trained by a deep convolutional GAN, and the deep convolutional GAN includes a discriminator, a generator, a switcher and a calculator; during training, the discriminator is connected to the generator through the switcher, and the generator generates an image training data sample for training the discriminator according to the training data sample, and the discriminator uses the image training data sample generated by the generator for training; during discrimination, the discriminator is connected to the image sensor through the switcher, and outputs the category of the combustible and the presence or absence of a fire source according to the image data provided by the image sensor. The discriminator includes a classifier, and the classifier is, for example, a CNN neural network. The classifier can be trained to perform the task of discriminating real data samples. The training data for the discriminator is similar to the actual data samples, but can be generated or modified to include the ability to present them as fake samples or artificial samples. The neural networks of the discriminator and the generator can generally be implemented by a multi-layer network, and the multi-layer network is composed of multiple processing layers, such as dense processing, batch normalization processing, activation processing, input reshaping processing, Gaussian dropout processing, Gaussian noise processing, two-dimensional convolution and two-dimensional upsampling.

[0056] In the present invention, the generator network can be regarded as a mapping from the data space to the image space. The discriminator network can be regarded as a mapping from the image space to the probability of the real data set. During training, the discriminator attempts to obtain results based on the input. Based on a series of results, both the discriminator and the generator can attempt to fine-tune their parameters to improve their operations. For example, if the discriminator makes a correct prediction, the generator can update its parameters to generate fake samples and deceive the discriminator. If the discriminator makes an incorrect prediction based on the fake samples, the discriminator can learn from the mistakes and avoid similar mistakes. Therefore, updating the discriminator and the generator can include a feedback process. This feedback process can be continuous or incremental. The generator and the discriminator can be executed iteratively to optimize data generation and image classification. In the incremental feedback process, the generator can be frozen first, and only the discriminator is trained until the discriminator reaches the optimal recognition result. During the frozen state of the generator, the discriminator can be trained to be optimized relative to the state of the generator. Then the discriminator is frozen and the generator is trained. Next, the generator is frozen and the discriminator is trained, and so on.

[0057] In the continuous feedback process, the discriminator can be trained in only one or several iterations, and the generator can be updated simultaneously with the discriminator.

[0058] If the distribution of the generated simulated data set can completely match the distribution of the real data set, the discriminator is maximally confused and cannot distinguish real samples from fake samples.

[0059] The present invention can determine whether the stopping condition is satisfied by evaluating whether the gradient is large enough. The generator of the present invention updates the network parameters through the backpropagation algorithm, and each layer of the generator has one or more gradients.

[0060] Specifically, the training of the deep convolutional neural network GAN includes the following process:

[0061] The fire element recognition model is trained by a deep convolutional neural network GAN. The deep convolutional neural network GAN includes a generator, a switcher, a discriminator, and a calculator. Its training process includes:

[0062] S2-1: Make the switcher act to connect the generator to the discriminator through the switcher;

[0063] S2-2: Make the generator generate correct image training samples including combustibles and ignition sources according to the training data samples;

[0064] S2-3: The discriminator discriminates according to the image training samples including combustibles and ignition sources to generate a discrimination result;

[0065] S2-4: The calculator calculates the loss function based on the current discrimination result and the training data sample, and judges that if the current loss function has not reached the minimum, step S2-9 is executed; if the current loss function reaches the minimum, step S2-5 is executed;

[0066] S2-5: The generator changes its network parameters and generates a fake image sample based on the training data sample;

[0067] S2-6: The discriminator discriminates based on the fake image sample to generate a discrimination result;

[0068] S2-7: The calculator calculates the loss function based on the current discrimination result and the training data sample, and judges that if the current loss function is the maximum, step S2-8 is executed; if the current loss function has not reached the maximum, step S2-9 is executed;

[0069] S2-8: End the training, and make the switch act so that the image sensor is connected to the discriminator through the switch;

[0070] S2-9: The calculator calculates the gradient of the loss function with respect to the current network parameters of the discriminator, and uses the gradient to update the current network parameters of the discriminator in a gradient ascent manner, and then returns to step S2-2.

[0071] Figure 3 is the block diagram of the automatic fire extinguishing device provided by the present invention. As Figure 3 shown, the automatic fire extinguishing device provided by the present invention includes a second control unit, a smoke exhaust module and a second communication unit. The smoke exhaust module includes a motor, a motor driver, an exhaust fan driver, an exhaust fan, and an emergency air inlet and a smoke exhaust port mechanism; the second communication unit is used for communication connection with the above-mentioned elevator car fire warning device. When the second control unit receives a detection instruction through the second communication unit, the second control unit provides an instruction to the motor driver, and the motor driver controls the motor to drive the emergency air inlet and the smoke exhaust port mechanism to operate to open the emergency air inlet and the smoke exhaust port, and then closes the emergency air inlet and the smoke exhaust port; the second control unit provides an instruction to the exhaust fan driver, and the exhaust fan driver controls the exhaust fan to operate, and then stops operating. Preferably, the fire extinguishing and smoke exhaust instructions are sent to the second control unit. The second control unit causes the ignition unit to ignite the potassium ion fire extinguishing agent particles in the fire extinguishing agent cylinder according to the fire extinguishing instruction, sends an instruction to the servo mechanism according to the smoke exhaust instruction, opens the emergency air inlet and the exhaust port of the elevator car, and provides an instruction to the exhaust fan, and the exhaust fan discharges the smoke in the elevator car from the exhaust port.

[0072] The automatic fire extinguishing device further includes an ignition unit and a fire extinguishing agent cylinder. When the second control unit receives the fire extinguishing and smoke exhaust instructions through the second communication unit, according to the fire extinguishing instruction, the second control unit makes the ignition unit ignite the potassium ion fire extinguishing agent particles in the fire extinguishing agent cylinder, and according to the smoke exhaust instruction, provides an instruction to the motor driver. The motor driver controls the motor to drive the emergency air inlet and smoke exhaust port mechanism to operate and open the emergency air inlet and smoke exhaust port until the fire is eliminated; the second control unit provides an instruction to the exhaust fan driver, and the exhaust fan driver controls the exhaust fan to operate until the fire is eliminated.

[0073] In the present invention, the automatic fire extinguishing device further includes an input unit for a user to input fire extinguishing and smoke exhaust instructions. The input unit is installed on the inner wall of the elevator car for easy operation by the user in case of emergency. A protective shell is provided outside the input unit to prevent misoperation.

[0074] In the present invention, the fire extinguishing agent is a potassium ion fire extinguishing agent. The potassium ion fire extinguishing agent formula uses food-grade raw materials and is safe and harmless to the human body. Its fire extinguishing principle is as follows: The ionized potassium oxide released by the combustion of the potassium ion fire extinguishing agent has a uniform omnidirectional effect, achieving full flooding to cover the entire protected area. When it contacts the fire source, it combines with the flame free radicals, repeatedly cuts off the flame free radical reaction chain, forms stable non-combustible products, and ultimately causes the flame chain to break, achieving the purpose of extinguishing the fire without consuming the environmental oxygen content. The gas released by the potassium ion fire extinguishing agent can be suspended in the protected room or housing for at least 30 minutes, effectively and continuously suppressing the expansion or reignition of the fire.

[0075] The potassium ion fire extinguishing agent, which is safe and non-toxic, can cope with five categories of fires, is stored at a temperature of -60~+160°C, is not afraid of jolts and vibrations, is stored in a solid state, and will only start when the temperature exceeds 410°C. When ignited, it changes from a solid state to a gaseous state and releases.

[0076] In the present invention, the automatic fire extinguishing device further includes a second storage unit for storing control programs and data. The control programs include control programs for the motor driver, exhaust fan driver, ignition unit, and second communication unit. The control programs are also used to process the instructions input by the input unit and generate control programs for the motor driver, exhaust fan driver, ignition unit, and second communication unit according to the input instructions.

[0077] 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 the descriptions in the specification only illustrate the principles of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. An elevator car fire alarm, characterized in that: The invention comprises a detection unit and a first control unit, wherein the detection unit comprises a sensor array; the first control unit comprises a fire element recognition model and a fire recognition model, wherein the fire element recognition model obtains K fire elements according to information provided by the sensor array; the fire recognition model estimates the probability of fire according to the K fire element quantified data provided by the fire element recognition model, and the fire recognition model is trained by a probability model, and the process comprises: S1-1: Obtain the quantitative data of the series of fire elements in the elevator car in the past and form a data vector , n is a positive integer greater than or equal to 2; K is a positive integer greater than or equal to 2; S1-2: Construct a probability model p of fire occurrence: ， In the formula, , Represents the quantitative data about the kth fire element A scalar function of is a parameter; S1-3: Estimation The best parameters : ， In the formula, is the likelihood function, whose gradient is: ； , Express The gradient of Express expectations; Express expectations; S1-4: From the data vector Get a set of positive samples from , m is a positive integer less than or equal to n; a set of negative samples is obtained according to the following formula : ， In the formula, To set the coefficient, For the transformation relationship; S1-5: Update by the following formula : , In the formula, is the learning coefficient; S1-6: According to the updated Get the fire identification model: 。 2. The elevator car fire alarm according to claim 1, characterized in that: , In the formula, represents the divergence, express Space for change; Indicates when The distribution of hour The empirical distribution of .

3. The elevator car fire alarm according to claim 1, characterized in that: The fire element recognition model is trained by a deep convolutional neural network GAN, which includes a generator, a switcher, a discriminator and a calculator. The training process includes: S2-1: The switch is activated so that the generator is connected to the discriminator through the switch; S2-2: enabling the generator to generate correct image training samples including combustibles and fire sources according to the training data samples; S2-3: The discriminator performs identification based on the image training samples including combustibles and fire sources to generate identification results; S2-4: The calculator calculates the loss function based on the current identification result and the training data sample, and determines that if the current loss function has not reached the minimum, step S2-9 is executed, if the current loss function reaches the minimum, step S2-5 is executed; S2-5: Make the generator change its network parameters and generate fake image samples based on the training data samples; S2-6: The discriminator performs identification based on the fake image sample to generate an identification result; S2-7: The calculator calculates the loss function based on the current identification result and the training data sample, and determines that if the current loss function is the minimum, step S2-8 is executed, if the current loss function does not reach the minimum, step S2-9 is executed; S2-8: End the training and make the switch act so that the image sensor is connected to the discriminator through the switch; S2-9: The calculator calculates the gradient of the loss function with respect to the current network parameters of the discriminator, uses the gradient to update the current network parameters of the discriminator by gradient boosting, and then returns to step S2-2.

4. The elevator car fire alarm according to claim 3, characterized in that: It also includes an audible and visual alarm. The first control unit causes the audible and visual alarm to display a light signal corresponding to the probability value of a fire, and to send out a sound signal corresponding to the probability value of a fire.

5. The elevator car fire alarm according to any one of claims 1 to 4, characterized in that: It also includes a first communication unit. When the probability of fire is greater than or equal to a first threshold, the first control unit sends a detection instruction to the automatic fire extinguisher through the first communication unit to detect whether the smoke exhaust module is in good condition; and sends an early warning message to the host computer at the same time.

6. The elevator car fire alarm according to claim 5, characterized in that: When the probability of fire is greater than or equal to a second threshold, the first control unit sends fire extinguishing and smoke exhaust instructions to the automatic fire extinguisher, and sends elevator car fire extinguishing and smoke exhaust information to the host computer, and the second threshold is greater than the first threshold.

7. An automatic fire extinguishing device, characterized in that: It includes a second control unit, a smoke exhaust module and a second communication unit. The smoke exhaust module includes a motor, a motor driver, an exhaust fan driver, an exhaust fan and an emergency air inlet and smoke exhaust port mechanism. The second communication unit is used to communicate with the elevator car fire alarm according to claim 6. When the second control unit receives a detection instruction through the second communication unit, the second control unit provides instructions to the motor driver, and the motor driver controls the motor to drive the emergency air inlet and smoke exhaust port mechanism to open the emergency air inlet and smoke exhaust port, test run the set time, and then close the emergency air inlet and smoke exhaust port. The second control unit provides instructions to the exhaust fan driver, and the exhaust fan driver controls the exhaust fan to run, test run the set time, and then stop running.

8. The automatic fire extinguishing device according to claim 7, characterized in that: It also includes an ignition unit and a fire extinguishing agent cartridge. When the second control unit receives a fire extinguishing and smoke exhaust instruction through the second communication unit, the second control makes the ignition unit ignite the potassium ion fire extinguishing agent particles in the fire extinguishing agent cartridge according to the fire extinguishing instruction, and provides instructions to the motor driver according to the smoke exhaust instruction. The motor driver controls the motor to drive the emergency air inlet and smoke exhaust port mechanism to open the emergency air inlet and smoke exhaust port; the second control unit provides instructions to the exhaust fan driver, and the exhaust fan driver controls the operation of the exhaust fan.

9. The automatic fire extinguishing device according to claim 8, characterized in that: It also includes an input unit, which is used for a user to input fire extinguishing and smoke exhausting instructions.

10. The automatic fire extinguishing device according to claim 9, characterized in that: The fire extinguishing agent is potassium ion fire extinguishing agent.

Images