Photoelectric smoke detector detection methods, systems and storage media

Abstract

This invention discloses a detection method, system, and storage medium for photoelectric smoke detectors, relating to the field of detector detection. By performing static and dynamic smoke simulations on the final test piezoelectric element, the invention tests the response capability and sensitivity of the photoelectric smoke detector from both static and dynamic perspectives, improving the comprehensiveness of the test. The test results can thus accurately reflect whether the photoelectric smoke detector needs repair or replacement. Furthermore, by employing a tuna optimization algorithm to iterate multiple parameters of the piezoelectric element multiple times simultaneously, and using the error between the abrupt change time of the piezoelectric element and the abrupt change time of the actual smoke as the fitness function, the error between the abrupt change time of the piezoelectric element and the abrupt change time of the actual smoke decreases with each iteration, ultimately meeting the simulation requirements.

Description

Technical Field

[0001] This invention belongs to the field of detector detection, and more specifically, it relates to a detection method, system and storage medium for photoelectric smoke detectors. Background Technology

[0002] Photoelectric smoke detectors typically utilize the principle of light scattering. When smoke particles enter the detection chamber, they scatter the light emitted by a light source, which is detected by a photosensitive element, triggering an alarm. However, in actual testing, it may be necessary to simulate smoke of different concentrations to verify the detector's sensitivity. This can be difficult to control in a real environment or requires repeated experiments, resulting in high costs. Existing tests for the sensitivity of photoelectric smoke detectors do not assess their response capabilities and sensitivity from both static and dynamic perspectives, making the tests incomplete. Consequently, the test results cannot accurately reflect whether the photoelectric smoke detector under test needs repair or replacement. Summary of the Invention

[0003] In response to the problems in related technologies, this invention proposes a photoelectric smoke detector detection method, system, and storage medium to overcome the aforementioned technical problems existing in the prior art.

[0004] To solve the above-mentioned technical problems, the present invention is achieved through the following technical solution:

[0005] This invention relates to a photoelectric smoke detector detection method based on piezoelectric element adjustment, comprising the following steps:

[0006] S1. Collect several sets of smoke concentration change data corresponding to the sudden changes in concentration and several scattered light intensity change data of the candidate piezoelectric sheets to obtain smoke concentration change dataset and candidate piezoelectric sheet scattered light intensity change data matrix.

[0007] S2. Combined with the data collected by S1, and by collecting historical data on the impact of changes in the piezoelectric element's structure on response speed parameters, scattered light intensity before and after the abrupt change, and abrupt change time, a piezoelectric element response time mapping model is constructed; and the parameters of the corresponding candidate piezoelectric elements are adjusted to obtain the final test piezoelectric element.

[0008] S3. Static smoke simulation was performed using the final test piezoelectric element to assess the performance stability of the photoelectric smoke detector under test when the measured concentration was fixed; then, dynamic smoke simulation was performed using the final test piezoelectric element to assess the performance stability of the photoelectric smoke detector under test when the measured concentration changed abruptly.

[0009] Because piezoelectric elements can precisely control the intensity of scattered light, which reflects the light absorption effect of smoke of different concentrations, they are used instead of real smoke. By adjusting the optical properties of the piezoelectric elements, smoke of different concentrations can be simulated, thus providing controllable testing conditions in a laboratory environment. This approach offers high repeatability, stable testing conditions, and eliminates the need to generate actual smoke, making it more environmentally friendly and safer. By conducting static and dynamic smoke simulations on the final tested piezoelectric elements, the response capability and sensitivity of the photoelectric smoke detector under test are tested from both static and dynamic perspectives. This improves the comprehensiveness of the test, and the test results can more accurately reflect whether the photoelectric smoke detector under test needs repair or replacement.

[0010] Preferably, the shape of the piezoelectric element is changed by altering the voltage applied to each candidate piezoelectric element, thereby obtaining a matrix of abrupt changes in the scattered light intensity of the candidate piezoelectric element.

[0011] By collecting a dataset of sudden changes in smoke concentration and a matrix of sudden changes in scattered light intensity of candidate piezoelectric elements, we can provide data support for the subsequent screening of piezoelectric elements in the candidate piezoelectric element set.

[0012] Preferably, step S2 includes the following steps:

[0013] S21. When the error between the scattered light intensity mutation data matrix of the candidate piezoelectric element and the corresponding data in the smoke concentration mutation data is less than the response time error threshold, the candidate piezoelectric element corresponding to the error data is taken as the final test piezoelectric element; otherwise, the parameters of the candidate piezoelectric element corresponding to the error data are adjusted until the error between the scattered light intensity mutation data matrix of the candidate piezoelectric element and the corresponding data in the smoke concentration mutation data is less than the response time error threshold; thus obtaining the final test piezoelectric element.

[0014] Because different piezoelectric elements have a certain response time when the applied voltage is suddenly adjusted, due to the performance of the piezoelectric element and the influence of the external environment, the response time of the piezoelectric element needs to be taken into account in order to better simulate the actual smoke concentration. Therefore, by screening and adjusting relevant parameters, the response time of the corresponding piezoelectric element is made to meet the actual simulation requirements.

[0015] Preferably, adjusting the parameters of the candidate piezoelectric element corresponding to the error data in step S21 includes the following steps:

[0016] S211. Collect multiple sets of historical data on the impact of changes in the piezoelectric element's scattered light intensity on the response speed, scattered light intensity data before and after the change, and the time taken for the change to construct a piezoelectric element response time mapping model. In conjunction with the piezoelectric element response time mapping model, adjust the parameters of the candidate piezoelectric element corresponding to the error data in S21 to obtain the final test piezoelectric element.

[0017] By setting several parameters that affect the response speed of the piezoelectric element, the adjustment targets for adjusting the response speed of the piezoelectric element are determined. By constructing a piezoelectric element response time mapping model, the corresponding response time data can be mapped out in a timely manner when adjusting the parameters of the initially tested piezoelectric element, so as to know the effect of parameter adjustment and make subsequent adjustments, thereby improving the adjustment efficiency and feasibility.

[0018] Preferably, the piezoelectric element response time mapping model in S211 adopts the SVM model;

[0019] The SVM (Support Vector Machine) model can map data from a low-dimensional space to a high-dimensional space, and build a linear classifier in the high-dimensional space, thus solving the problem of nonlinear separability. The training process is relatively stable and it is not easy to get stuck in local optima, thereby improving the stability and reliability of the model. It is relatively robust to noisy data, that is, it has low sensitivity to outliers and noise points. It has strong interpretability, as it classifies data by finding an optimal hyperplane, the position and orientation of which can be intuitively understood as the classification boundary of the data.

[0020] Preferably, the parameter adjustment in S211 uses the tuna optimization algorithm;

[0021] The tuna optimization algorithm employs both spiral and parabolic foraging strategies, enabling rapid location of potential optimal solutions within the search space. The spiral foraging strategy allows individuals to explore extensively within the search space, increasing the probability of finding the global optimum. It is insensitive to the selection of the initial population and has relatively low requirements for parameter settings; small changes in parameters typically do not significantly impact the algorithm's performance. Based on these advantages, this scheme uses the tuna optimization algorithm to iterate multiple parameters of the piezoelectric element simultaneously, stopping at each step. The fitness function is used as the error between the abrupt change time of the piezoelectric element and the abrupt change time of the actual smoke. Therefore, as the iteration progresses, the error between the abrupt change time of the piezoelectric element and the abrupt change time of the actual smoke decreases, ultimately meeting the simulation requirements.

[0022] Preferably, step S3 includes the following steps:

[0023] S31. The light intensity data of the final test piezoelectric element for static smoke simulation is collected multiple times using the photoelectric smoke detector under test to obtain a fixed light intensity data matrix.

[0024] S32. Combine the fixed light intensity data matrix to provide early warning and alarm for the maintenance, replacement, and repair of the photoelectric smoke detector under test;

[0025] S33. When the photoelectric smoke detector under test has not been repaired, replaced, or given an early warning or alarm, the photoelectric smoke detector under test is used to collect light intensity data from the final test piezoelectric element used for dynamic smoke simulation multiple times to obtain a dynamic light intensity data matrix.

[0026] S34. Based on the dynamic light intensity dataset, perform maintenance, replacement, early warning, and alarm functions again for the photoelectric smoke detector under test;

[0027] Since the actual smoke concentration is constantly changing, and the intensity of scattered light caused by the change in the piezoelectric element structure needs to be dynamically adjusted to change it dynamically, this solution tests the response capability and sensitivity of the photoelectric smoke detector under test from both static and dynamic perspectives by performing static and dynamic smoke simulations on the final test piezoelectric element. This improves the comprehensiveness of the test, and the test results can more accurately reflect whether the photoelectric smoke detector under test needs to be repaired or replaced.

[0028] Preferably, step S32 includes the following steps:

[0029] S321. Calculate the standard deviation of each row of data in the fixed light intensity data matrix to obtain the current light intensity standard deviation dataset.

[0030] An alarm signal is issued when there is a current received light intensity standard deviation data in the current received light intensity standard deviation dataset that is greater than or equal to the first received light intensity discrete threshold. When there is only a current received light intensity standard deviation data in the current received light intensity standard deviation dataset that is less than the first received light intensity discrete threshold but greater than or equal to the second received light intensity discrete threshold, the data in the fixed received light intensity data matrix corresponding to the current received light intensity standard deviation data is used as the fixed received light intensity data matrix set to be predicted, and the process proceeds to S322. If there is no current received light intensity standard deviation data in the current received light intensity standard deviation dataset that is greater than or equal to the second received light intensity discrete threshold, S31 and S32 are repeated.

[0031] S322. Set several future time points to obtain a first set of future time points; predict the fixed light intensity data of future time points based on the first set of future time points and the set of fixed light intensity data matrix to be predicted using a BP neural network model to obtain a future fixed light intensity data matrix; calculate the standard deviation of each row of data in the future fixed light intensity data matrix to obtain a future light intensity standard deviation dataset.

[0032] S323. Set the first time difference threshold and the second time difference threshold;

[0033] When there is a future light intensity standard deviation data in the future light intensity standard deviation dataset that is greater than or equal to the first light intensity discrete threshold, the future time corresponding to the future light intensity standard deviation data is recorded as the first future time; when the difference between the first future time and the present time is greater than or equal to the first time difference threshold, a level one warning is issued; when the difference between the first future time and the present time is less than the first time difference threshold but greater than or equal to the second time difference threshold, a level two warning is issued; when the difference between the first future time and the present time is less than the second time difference threshold, a level three warning is issued.

[0034] Level 1 warnings are used to alert the user; Level 2 warnings are used to prepare for repair or replacement; and Level 3 warnings are used for early repair and replacement. An alarm is triggered based on the degree of error between the detection data of the photoelectric smoke detector under test and the actual set data. This allows for timely reminders to maintenance personnel for repair or replacement, ensuring the normal operation of the photoelectric smoke detector under test. Furthermore, by repeatedly collecting data on the error between the detection data and the actual set data, the error data for future moments can be predicted. This allows for advance knowledge of the potential for malfunction and the expected timing of the malfunction, facilitating different levels of early warning and enabling the implementation of appropriate countermeasures.

[0035] Preferably, step S34 includes the following steps:

[0036] S341. Set a first and a second discrete threshold for light received intensity; calculate the standard deviation of the light received intensity data before and after the current change in the dynamic light received intensity dataset; if there is a standard deviation data that is greater than or equal to the first discrete threshold for light received intensity, issue an alarm signal; if there is only a standard deviation data that is less than the first discrete threshold for light received intensity and greater than or equal to the second discrete threshold for light received intensity, proceed to S342; if there is no standard deviation data that is greater than or equal to the second discrete threshold for light received intensity, repeat S33 and S34.

[0037] S342. Based on the dynamic light intensity data matrix, predict the light intensity data before and after the abrupt change at future time points, and calculate the standard deviation of the light intensity data before and after the abrupt change at each future time point; when there is a standard deviation data that is greater than or equal to the first light intensity discrete threshold, if the difference between the future time and the present time corresponding to the light intensity standard deviation data is greater than or equal to the first time difference threshold, issue a level one warning; if the difference is less than the first time difference threshold but greater than or equal to the second time difference threshold, issue a level two warning; if the difference is less than the second time difference threshold, issue a level three warning.

[0038] By dynamically setting the intensity of scattered light caused by changes in the piezoelectric element structure, the response capability of the photoelectric smoke detector under test to sudden changes in smoke concentration is detected. Specifically, by calculating the standard deviation of multiple detection results from the photoelectric smoke detector under test under identical conditions, the stability of the detection results can be determined. If unstable, i.e., the calculated standard deviation exceeds the first light intensity dispersion threshold, it indicates a change in the performance of the light-emitting or receiving tube or a possible circuit malfunction, triggering an alarm to promptly remind relevant personnel to repair or replace it. Conversely, for cases where the calculated standard deviation does not exceed the first light intensity dispersion threshold, the light intensity data at future times is predicted and the standard deviation is calculated. Different levels of warning are then issued based on the difference between the future time when the first light intensity dispersion threshold is reached and the present time, prompting relevant personnel to take appropriate measures, thereby ensuring the normal operation of the photoelectric smoke detector under test.

[0039] The photoelectric smoke detector detection system based on piezoelectric element adjustment includes a smoke concentration change data acquisition module, a candidate piezoelectric element scattered light intensity change data acquisition module, a response time mapping model construction module, a candidate piezoelectric element parameter adjustment module, a photoelectric smoke detector static performance detection module, and a photoelectric smoke detector dynamic performance detection module.

[0040] The present invention has the following beneficial effects:

[0041] 1. In this invention, by performing static and dynamic smoke simulations on the final test piezoelectric element, the response capability and sensitivity of the photoelectric smoke detector under test are tested from both static and dynamic perspectives, which improves the comprehensiveness of the test. Thus, the test results can more accurately reflect whether the photoelectric smoke detector under test needs to be repaired or replaced.

[0042] 2. In this invention, the response time of the structural change of the piezoelectric element is taken into account to better simulate the actual smoke concentration; by screening and adjusting the relevant parameters, the response time of the corresponding piezoelectric element is made to meet the actual simulation requirements.

[0043] 3. In this invention, by constructing a piezoelectric element response time mapping model, the corresponding response time data can be mapped out in a timely manner when the parameters of the initially tested piezoelectric element are adjusted, so as to know the effect of parameter adjustment and make subsequent adjustments, thereby improving the adjustment efficiency and feasibility.

[0044] 4. In this invention, the tuna optimization algorithm is used to iterate multiple parameters of the piezoelectric element multiple times simultaneously, and the error between the change time of the piezoelectric element and the change time of the actual smoke is used as the fitness function. Therefore, as the iteration proceeds, the error between the change time of the piezoelectric element and the change time of the actual smoke becomes smaller and smaller, eventually meeting the simulation requirements.

[0045] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0046] To more clearly illustrate the technical solutions of the embodiments of the invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0047] Figure 1 This is a schematic diagram of the overall process of the photoelectric smoke detector detection method based on piezoelectric element adjustment according to the present invention;

[0048] Figure 2 This is a schematic flowchart of the photoelectric smoke detector detection method based on piezoelectric element adjustment according to the present invention;

[0049] Figure 3 This is a schematic diagram of the process for screening piezoelectric elements according to the present invention;

[0050] Figure 4 This is a schematic diagram of the process for static performance testing of the photoelectric smoke detector under test according to the present invention;

[0051] Figure 5 This is a schematic diagram of the process for dynamic performance testing of the photoelectric smoke detector under test according to the present invention.

[0052] Figure 6 This is a schematic diagram of the detection system of the photoelectric smoke detector based on piezoelectric adjustment according to the present invention. Detailed Implementation

[0053] The technical solutions of the embodiments of the invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the invention, and not all embodiments. Based on the embodiments of the invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the invention.

[0054] Example 1

[0055] Please see Figure 1-5This embodiment describes a photoelectric smoke detector detection method based on piezoelectric element adjustment, comprising the following steps:

[0056] S1. Collect several sets of smoke concentration change data corresponding to the sudden changes in concentration and several scattered light intensity change data caused by structural changes of the candidate piezoelectric sheet, and obtain smoke concentration change dataset and candidate piezoelectric sheet scattered light intensity change data matrix.

[0057] S1 includes the following steps:

[0058] S11. Set several candidate piezoelectric elements to obtain a candidate piezoelectric element set; use a concentration sensor to collect several sets of smoke concentration change data corresponding to sudden concentration changes, and obtain smoke concentration sudden change dataset a; as follows.

[0059] a={(a 11 ,a 12 ,a 13 ),...,(a i1 ,a i2 ,a i3 ),...,(a a′1 ,a a′2 ,a a′3 )};

[0060] Among them, a i1 a i2 a i3 ...

[0061] S12. In conjunction with the smoke concentration mutation dataset and the set of candidate piezoelectric sheets, under the same conditions, the shape of the piezoelectric sheet is changed by changing the voltage applied to each candidate piezoelectric sheet, thereby changing the corresponding scattered light intensity to simulate the smoke concentration data of each concentration mutation, and obtain the candidate piezoelectric sheet scattered light intensity mutation data matrix.

[0062] S2. By collecting historical data on the influence of changing the applied voltage of the piezoelectric element on the response speed of the structure, as well as the scattered light intensity data before and after the abrupt change, and the abrupt change time data, a piezoelectric element response time mapping model is constructed. The Euclidean distance between the scattered light intensity abrupt change data matrix of the candidate piezoelectric element and the smoke concentration abrupt change data dataset is calculated, and the parameters of the corresponding candidate piezoelectric element are adjusted in combination with the piezoelectric element response time mapping model to obtain the final test piezoelectric element.

[0063] S2 includes the following steps:

[0064] S21. Calculate the Euclidean distance between the time consumption data in each row of the scattered light intensity mutation data matrix of the candidate piezoelectric element and the time consumption data in the smoke concentration mutation dataset to obtain the time consumption Euclidean distance dataset. This represents the Euclidean distance between the time-consuming data in the j-th data point of the candidate piezoelectric element scattered light intensity mutation data matrix and the time-consuming data in the smoke concentration mutation dataset. This indicates the total number of piezoelectric elements to be selected; the calculation formula is as follows:

[0065]

[0066] S22. Set a response time error threshold; when the smallest Euclidean distance data in the time-consuming Euclidean distance data set is less than the response time error threshold, the candidate piezoelectric piece corresponding to the smallest time-consuming Euclidean distance data is taken as the final test piezoelectric piece; otherwise, the parameters of the candidate piezoelectric piece corresponding to the smallest time-consuming Euclidean distance data are adjusted to obtain the final test piezoelectric piece.

[0067] The adjustment of the parameters of the candidate piezoelectric element corresponding to the minimum time-consuming Euclidean distance data in S22 includes the following steps:

[0068] S221. Several parameters that affect the response speed of structural changes in the piezoelectric element are set to obtain a set of parameters affecting the piezoelectric element's response speed. The set of parameters affecting the piezoelectric element's response speed includes piezoelectric coefficient, elastic modulus, density, and the frequency and amplitude of the driving voltage. In conjunction with the set of parameters affecting the piezoelectric element's response speed, multiple sets of historical data on the response speed of changing the applied voltage of the piezoelectric element to change the intensity of scattered light, scattered light intensity data before the change, scattered light intensity data after the change, and change time data are collected to obtain a historical response speed affecting parameter data matrix, a historical scattered light intensity dataset before the change, a historical scattered light intensity dataset after the change, and a historical change time dataset.

[0069] S222. A piezoelectric element response time mapping model is constructed using the historical response speed influence parameter data matrix, the historical pre-abrupt scattered light intensity dataset, the historical post-abrupt scattered light intensity dataset, and the historical abrupt change time dataset.

[0070] S222 includes the following steps:

[0071] S2221. Construct an initial SVM model and set the training data ratio; according to the training data ratio, divide the historical response speed influence parameter data matrix, historical pre-mutation scattered light intensity dataset, historical post-mutation scattered light intensity dataset, and historical mutation time dataset to obtain the historical response speed influence parameter training data matrix, historical pre-mutation scattered light intensity training dataset, historical post-mutation scattered light intensity training dataset, historical mutation time training dataset, historical response speed influence parameter test data matrix, historical pre-mutation scattered light intensity test dataset, historical post-mutation scattered light intensity test dataset, and historical mutation time test dataset.

[0072] S2222. Set a training error threshold; input the historical response speed influence parameter training data matrix, the historical pre-abrupt scattering intensity training dataset, the historical post-abrupt scattering intensity training dataset as training data, and the historical abrupt change time training dataset as training labels into the initial SVM model for training; during the training process, when the training error is less than the training error threshold, stop training and obtain the trained SVM model; otherwise, continue training until the training error is less than the training error threshold;

[0073] S2223. Set a test accuracy threshold; input the historical response speed influence parameter test data matrix, the historical pre-abrupt scattering intensity test dataset, and the historical post-abrupt scattering intensity test dataset as test data, and the historical abrupt change time test dataset as test labels into the trained SVM model for testing; after the test is completed, obtain the test accuracy data; when the test accuracy data is greater than or equal to the test accuracy threshold, use the trained SVM model as the piezoelectric element response time mapping model; otherwise, return to S2222 to train the trained SVM model until the test accuracy data is greater than or equal to the test accuracy threshold.

[0074] S223. The candidate piezoelectric element corresponding to the smallest Euclidean distance data in the time-consuming Euclidean distance dataset is recorded as the initial test piezoelectric element; the parameters of the initial test piezoelectric element are adjusted in conjunction with the piezoelectric element response speed influence parameter type set and the piezoelectric element response time mapping model. After the adjustment is completed, the final test piezoelectric element is obtained.

[0075] S223 involves adjusting the parameters of the initial test piezoelectric element in conjunction with the set of parameter types affecting the piezoelectric element's response speed and the piezoelectric element's response time mapping model, including the following steps:

[0076] S2231. Based on the set of parameter types affecting the piezoelectric element response speed, obtain the value ranges of various types of parameter data for the initial test piezoelectric element, thus obtaining the set of parameter value ranges b for the test piezoelectric element; as follows.

[0077]

[0078] in, These represent the lower and upper limits of the parameters for the i-th type of the initial test piezoelectric element, respectively, and b′ represents the total number of parameters that affect the response speed of the piezoelectric element.

[0079] Construct a tuna population for adjusting the piezoelectric element response speed parameters; set the maximum number of iterations for the tuna population for adjusting the piezoelectric element response speed parameters to be [value missing]. And the current iteration number is These are respectively denoted as the maximum number of iterations for response adjustment and the current number of iterations for response adjustment; the search space dimension of the tuna population for adjusting the piezoelectric sheet response speed parameter is the same as that of b′; S2232, set the initial position of each tuna in the tuna population for adjusting the piezoelectric sheet response speed parameter according to the set of test piezoelectric sheet parameter value intervals, and obtain the first initial position matrix;

[0080] The formula for generating the formula is as follows:

[0081]

[0082] In the formula, The piezoelectric response speed parameter adjustment represents the initial position of the j-th tuna in the tuna population along the parameter dimension of the i-th type of the initial test piezoelectric element, where c represents the size of the tuna population adjusted by the piezoelectric response speed parameter, and rand. 1ji Indicating targeting Generate random numbers between 0 and 1;

[0083] S2233. Set the piezoelectric element response speed parameter to adjust the fitness function c1′ of the tuna population; as follows.

[0084]

[0085] In the formula, This represents the Euclidean distance between the response time dataset obtained by mapping the piezoelectric response speed parameters and the time Euclidean distance dataset corresponding to the smallest time Euclidean distance data in the candidate piezoelectric scattered light intensity mutation data matrix, which are updated in each iteration, and the time data in the smoke concentration mutation dataset.

[0086] S2234. Begin iteration. Before iteration, set the current iteration count of the response adjustment to 1. During the first iteration, use the piezoelectric plate response speed parameter to adjust the fitness function c1′ of the tuna population to calculate the fitness value of the initial position of each tuna in the first initial position matrix, obtaining the first fitness value set. Take the largest fitness value in the first fitness value set and the corresponding initial position of the tuna as the first global best fitness and the first global best position, respectively. Update the initial position of each tuna in the first initial position matrix according to the first global best fitness and the first global best position. After the update is completed, increment the current iteration count of the response adjustment by 1 and enter the next iteration.

[0087] In each iteration, the fitness function c1′ of the piezoelectric response speed parameter adjustment tuna population is used to calculate the fitness value of each tuna position in the piezoelectric response speed parameter adjustment tuna population updated in the previous iteration, resulting in a second fitness value set. The maximum fitness value in the second fitness value set and the corresponding tuna position are taken as the second global optimal fitness and the second global optimal position, respectively. The position of each tuna in the piezoelectric response speed parameter adjustment tuna population updated in the previous iteration is updated according to the second global optimal fitness and the second global optimal position. After the update is completed, the current iteration number of the response adjustment is incremented by 1 and the next iteration is started.

[0088] S2235, when If the first final global best fitness and the first final global best position are obtained, stop the iteration; otherwise, continue the iteration until... Up to the point where; the first final global optimal fitness is used as the minimum optimized time Euclidean distance; when the minimum optimized time Euclidean distance is less than the response time error threshold, the parameters of the initial test piezoelectric sheet are set according to each position component of the first final global optimal position to obtain the final test piezoelectric sheet; otherwise, return to S2234 to continue iterating until the minimum optimized time Euclidean distance is less than the response time error threshold;

[0089] S3. Static smoke simulation was performed using the final test piezoelectric element to assess the performance stability of the photoelectric smoke detector under test when the measured concentration was fixed; then, dynamic smoke simulation was performed using the final test piezoelectric element to assess the performance stability of the photoelectric smoke detector under test when the measured concentration changed abruptly.

[0090] S3 includes the following steps:

[0091] S31. Set the desired scattered light intensity and the photoelectric smoke detector to be tested; fix the final test piezoelectric element according to the desired scattered light intensity and perform static smoke simulation; then use the photoelectric smoke detector to be tested to periodically and continuously collect light intensity data from the final test piezoelectric element that has performed static smoke simulation to obtain a fixed light intensity data matrix.

[0092] S32. Set a first light intensity discrete threshold and a second light intensity discrete threshold; perform maintenance and replacement early warning and alarm for the photoelectric smoke detector under test based on the first light intensity discrete threshold, the second light intensity discrete threshold and the fixed light intensity data matrix;

[0093] S32 includes the following steps:

[0094] S321. Calculate the standard deviation of each row of data in the fixed light intensity data matrix to obtain the current light intensity standard deviation dataset.

[0095] An alarm signal is issued when there is a current received light intensity standard deviation data in the current received light intensity standard deviation dataset that is greater than or equal to the first received light intensity discrete threshold. When there is only a current received light intensity standard deviation data in the current received light intensity standard deviation dataset that is less than the first received light intensity discrete threshold but greater than or equal to the second received light intensity discrete threshold, the data in the fixed received light intensity data matrix corresponding to the current received light intensity standard deviation data is used as the fixed received light intensity data matrix set to be predicted, and the process proceeds to S322. If there is no current received light intensity standard deviation data in the current received light intensity standard deviation dataset that is greater than or equal to the second received light intensity discrete threshold, S31 and S32 are repeated.

[0096] S322. Set several future time points to obtain a first set of future time points; predict the fixed light intensity data of future time points based on the first set of future time points and the set of fixed light intensity data matrix to be predicted using a BP neural network model to obtain a future fixed light intensity data matrix; calculate the standard deviation of each row of data in the future fixed light intensity data matrix to obtain a future light intensity standard deviation dataset.

[0097] S323. Set the first time difference threshold and the second time difference threshold;

[0098] When there is a future light intensity standard deviation data in the future light intensity standard deviation dataset that is greater than or equal to the first light intensity discrete threshold, the future time corresponding to the future light intensity standard deviation data is recorded as the first future time; when the difference between the first future time and the present time is greater than or equal to the first time difference threshold, a level one warning is issued; when the difference between the first future time and the present time is less than the first time difference threshold but greater than or equal to the second time difference threshold, a level two warning is issued; when the difference between the first future time and the present time is less than the second time difference threshold, a level three warning is issued.

[0099] S33. When the photoelectric smoke detector under test has not been repaired, replaced, warned, or alarmed, set the pre-abrupt scattering light intensity and the post-abrupt scattering light intensity; perform dynamic smoke simulation on the final test piezoelectric element based on the pre-abrupt scattering light intensity and the post-abrupt scattering light intensity; then periodically collect light intensity data from the final test piezoelectric element performing dynamic smoke simulation using the photoelectric smoke detector under test to obtain a dynamic light intensity data matrix.

[0100] S34. Set up a repair and replacement warning and alarm for the photoelectric smoke detector under test based on the first light intensity discrete threshold, the second light intensity discrete threshold and the dynamic light intensity dataset.

[0101] S34 includes the following steps:

[0102] S341. Calculate the standard deviation of the light intensity data before the current mutation and the light intensity data after the current mutation in the dynamic light intensity dataset to obtain the standard deviation dataset of the light intensity before the current mutation and the standard deviation dataset of the light intensity after the current mutation.

[0103] An alarm signal is issued when there is a standard deviation data in the current pre-mutation received light intensity standard deviation dataset or the current post-mutation received light intensity standard deviation dataset that is greater than or equal to the first received light intensity discrete threshold. When there is only a standard deviation data in the current pre-mutation received light intensity standard deviation dataset or the current post-mutation received light intensity standard deviation dataset that is less than the first received light intensity discrete threshold and greater than or equal to the second received light intensity discrete threshold, the current pre-mutation received light intensity standard deviation dataset and the current post-mutation received light intensity standard deviation dataset are respectively used as the current to-be-predicted pre-mutation received light intensity standard deviation dataset and the current to-be-predicted post-mutation received light intensity standard deviation dataset, and proceed to S342. If there is no standard deviation data in the current pre-mutation received light intensity standard deviation dataset or the current post-mutation received light intensity standard deviation dataset that is greater than or equal to the second received light intensity discrete threshold, S33 and S34 are repeated.

[0104] S342. Set several future time points to obtain a second set of future time points; based on the second set of future time points and the dynamic light intensity data matrix, use a BP neural network model to predict the light intensity data before and after the mutation at future time points to obtain a future dynamic light intensity data matrix; calculate the standard deviation of the light intensity data before and after the mutation at each future time point in the future dynamic light intensity data matrix to obtain a future light intensity standard deviation dataset before and after the mutation.

[0105] S343. When the standard deviation data of the received light intensity standard deviation dataset before the future mutation and the received light intensity standard deviation dataset after the future mutation are both greater than or equal to the first received light intensity discrete threshold, the future time corresponding to the received light intensity standard deviation data is recorded as the second future time. When the difference between the first future time and the present time is greater than or equal to the first time difference threshold, a first-level warning is issued. When the difference between the first future time and the present time is less than the first time difference threshold but greater than or equal to the second time difference threshold, a second-level warning is issued. When the difference between the first future time and the present time is less than the second time difference threshold, a third-level warning is issued.

[0106] Example 2

[0107] Please see Figure 6 This embodiment discloses a photoelectric smoke detector detection system based on piezoelectric element adjustment. The system can implement the method of the above embodiment, including a smoke concentration change data acquisition module, a candidate piezoelectric element scattered light intensity change data acquisition module, a response time mapping model construction module, a candidate piezoelectric element parameter adjustment module, a photoelectric smoke detector static performance detection module, and a photoelectric smoke detector dynamic performance detection module.

[0108] The smoke concentration mutation data acquisition module collects several sets of smoke concentration change data corresponding to the occurrence of concentration mutations, and obtains the smoke concentration mutation dataset.

[0109] The candidate piezoelectric element scattered light intensity mutation data acquisition module collects scattered light intensity mutation data caused by structural changes of several candidate piezoelectric elements based on the smoke concentration mutation dataset, and obtains a candidate piezoelectric element scattered light intensity mutation data matrix.

[0110] The response time mapping model construction module for the smoke concentration mutation dataset collects multiple sets of historical data on the impact of changing the applied voltage of the piezoelectric element on the response speed of the scattered light intensity, scattered light intensity data before the mutation, scattered light intensity data after the mutation, and mutation time data to construct a piezoelectric element response time mapping model.

[0111] The parameter adjustment module for the candidate piezoelectric element adjusts the parameters of the corresponding candidate piezoelectric element by calculating the Euclidean distance between each row of the scattered light intensity mutation data matrix of the candidate piezoelectric element and the smoke concentration mutation dataset, and by combining the piezoelectric element response time mapping model, thus obtaining the final test piezoelectric element.

[0112] The static performance testing module for photoelectric smoke detectors uses a static smoke simulation with a final test piezoelectric element to assess the performance stability of the photoelectric smoke detector under test when the smoke concentration is fixed.

[0113] The dynamic performance testing module for photoelectric smoke detectors uses a dynamic smoke simulation with a final test piezoelectric element to assess the performance stability of the photoelectric smoke detector under test when the measured concentration changes abruptly.

[0114] Example 3

[0115] This embodiment discloses a storage medium on which a program is stored. When the program is executed by a processor, it is used to implement the system described in the above embodiment.

[0116] In the description of this specification, references to terms such as "an embodiment," "example," "specific example," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0117] The preferred embodiments of the invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention.

Claims

1. A method for detecting a photoelectric smoke fire detector based on a piezoelectric sheet adjustment, characterized by, Comprising the following steps: S1, collecting a plurality of groups of concentration mutation corresponding smoke concentration change data and a plurality of selected piezoelectric sheet scattering light intensity mutation data, obtaining smoke concentration mutation data set and selected piezoelectric sheet scattering light intensity mutation data matrix; S2, cooperating with the data collected in S1, and through the collection of historical piezoelectric sheet structure change response speed influence parameter data, scattering light intensity data before mutation, scattering light intensity data after mutation and mutation time consumption data to construct piezoelectric sheet response time consumption mapping model; And adjust the parameters of the corresponding selected piezoelectric sheet to obtain the final test piezoelectric sheet; Specifically including: when the error between the selected piezoelectric sheet scattering light intensity mutation data matrix and the corresponding data in the smoke concentration mutation data set is less than the response time error threshold, the selected piezoelectric sheet corresponding to the error data is used as the final test piezoelectric sheet; Otherwise, adjust the parameters of the selected piezoelectric sheet corresponding to the error data until the error between the selected piezoelectric sheet scattering light intensity mutation data matrix and the corresponding data in the smoke concentration mutation data set is less than the response time error threshold, and the final test piezoelectric sheet is obtained; S3, the performance stability degree of the to-be-tested photoelectric smoke detector in the case of measuring concentration mutation is tested by using the final test piezoelectric sheet to simulate static smoke; And the performance stability degree of the to-be-tested photoelectric smoke detector in the case of measuring concentration mutation is tested by using the final test piezoelectric sheet to simulate dynamic smoke.

2. The photoelectric smoke fire detector detection method based on piezoelectric sheet adjustment according to claim 1, characterized in that: The scattering light intensity mutation data matrix of the selected piezoelectric sheet is obtained by changing the voltage applied to each selected piezoelectric sheet to change the shape of the piezoelectric sheet.

3. The photoelectric smoke fire detector detection method based on piezoelectric sheet adjustment according to claim 1, wherein, The parameter adjustment of the selected piezoelectric sheet corresponding to the error data in S2 includes the following steps: S211, collect a plurality of groups of historical piezoelectric sheet scattering light intensity change response speed influence parameter data, scattering light intensity data before mutation, scattering light intensity data after mutation and mutation time consumption data to construct piezoelectric sheet response time consumption mapping model; Cooperate with the piezoelectric sheet response time consumption mapping model to adjust the parameters of the selected piezoelectric sheet corresponding to the error data, and obtain the final test piezoelectric sheet.

4. The photoelectric smoke fire detector detection method based on piezoelectric sheet adjustment according to claim 3, characterized in that: The piezoelectric sheet response time consumption mapping model in S211 adopts SVM model.

5. The photoelectric smoke fire detector detection method based on piezoelectric sheet adjustment according to claim 4, characterized in that: The parameter adjustment in S211 adopts tuna optimization algorithm.

6. The photoelectric smoke fire detector detection method based on piezoelectric sheet adjustment according to claim 5, wherein, The S3 includes the following steps: S31, using the to-be-tested photoelectric smoke detector to collect light intensity data of the final test piezoelectric sheet for static smoke simulation multiple times, and obtaining a fixed light intensity data matrix; S32, combining the fixed light intensity data matrix to perform maintenance and replacement warning and alarm for the to-be-tested photoelectric smoke detector; S33, when the to-be-tested photoelectric smoke detector does not perform maintenance and replacement warning and alarm, using the to-be-tested photoelectric smoke detector to collect light intensity data of the final test piezoelectric sheet for dynamic smoke simulation multiple times, and obtaining a dynamic light intensity data matrix; S34, according to the dynamic light intensity data set, the maintenance and replacement warning and alarm for the to-be-tested photoelectric smoke detector are performed again.

7. The photoelectric smoke fire detector detection method based on piezoelectric sheet adjustment according to claim 6, characterized in that, The S34 includes the following steps: S341、set the first light intensity discrete threshold and the second light intensity discrete threshold; calculate the standard deviation of the current pre-mutation light intensity data and the current post-mutation light intensity data in the dynamic light intensity data set; if there is standard deviation data greater than or equal to the first light intensity discrete threshold, an alarm signal is sent; if there is only standard deviation data less than the first light intensity discrete threshold and greater than or equal to the second light intensity discrete threshold, S342 is entered; if there is no standard deviation data greater than or equal to the second light intensity discrete threshold, S33 and S34 are repeated; S342、predict the pre-mutation light intensity data and the post-mutation light intensity data at the future time points according to the dynamic light intensity data matrix, and calculate the standard deviation of the pre-mutation light intensity data and the post-mutation light intensity data at each future time point; when there is standard deviation data greater than or equal to the first light intensity discrete threshold, if the difference between the future time corresponding to the light intensity standard deviation data and the present time is greater than or equal to the first time difference threshold, a first-level warning is sent; if the difference is less than the first time difference threshold and greater than or equal to the second time difference threshold, a second-level warning is sent; if the difference is less than the second time difference threshold, a third-level warning is sent.

8. A system for implementing the photoelectric smoke fire detector detection method based on piezoelectric sheet adjustment according to any one of claims 1-7.

9. A storage medium having stored thereon a program which, when executed by a processor, causes the processor to perform the method of any one of claims 1 to 8. A photoelectric smoke fire detector detection method according to any one of claims 1-7.

Images