Photoelectric smoke fire detector detection method and system and storage medium thereof

Abstract

The invention discloses a photoelectric smoke fire detector detection method, a photoelectric smoke fire detector detection system and a storage medium of the photoelectric smoke fire detector detection system, and relates to the field of detector detection. The response capability and sensitivity of the photoelectric smoke fire detector to be tested are tested from static and dynamic angles, and the test comprehensiveness is improved, so that the test result can accurately reflect whether the photoelectric smoke fire detector to be tested needs to be maintained and replaced; a tuna optimization algorithm is adopted to simultaneously carry out multiple times of iteration stop on multiple parameters of the piezoelectric patch, and an error between the sudden change time consumption of the piezoelectric patch and the sudden change time consumption of actual smoke is used as a fitness function; therefore, along with iteration, the error between the sudden change time consumption of the piezoelectric plate and the sudden change time consumption of actual smoke is smaller and smaller, and finally the simulation requirement is met.

Description

Technical Field

[0001] The present invention belongs to the field of detector detection, and in particular, relates to a detection method and system for a photoelectric smoke fire detector and a storage medium thereof. Background Art

[0002] Photoelectric smoke fire detectors usually use the principle of light scattering. When smoke particles enter the detection chamber, they scatter the light emitted by the light source and are detected by the photosensitive element, thereby triggering an alarm. However, in actual testing, it may be necessary to simulate smoke of different concentrations to verify the sensitivity of the detector. This may be difficult to control in a real environment, or require repeated experiments, which is costly. In the existing sensitivity test of photoelectric smoke fire detectors, the response capability and sensitivity of the photoelectric smoke fire detectors are not tested from both static and dynamic perspectives, making the test not comprehensive. As a result, the test results cannot accurately reflect whether the photoelectric smoke fire detector under test needs to be repaired or replaced. Summary of the Invention

[0003] In response to the problems in the related art, the present invention proposes a photoelectric smoke fire detector detection method, system and storage medium thereof to overcome the above technical problems existing in the existing related art.

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

[0005] The present invention is a photoelectric smoke fire detector detection method based on piezoelectric piece adjustment, comprising the following steps:

[0006] S1. Collecting several sets of smoke concentration change data corresponding to sudden concentration changes and several sets of scattered light intensity sudden change data of selected piezoelectric sheets to obtain a smoke concentration sudden change data set and a matrix of scattered light intensity sudden change data of selected piezoelectric sheets;

[0007] S2, in conjunction with the data collected in S1, and by collecting historical data on the parameters affecting the response speed of the piezoelectric piece's structural change, the scattered light intensity data before the mutation, the scattered light intensity data after the mutation, and the mutation time consumption data, to build a piezoelectric piece response time consumption mapping model; and adjust the parameters of the corresponding candidate piezoelectric piece to obtain the final test piezoelectric piece;

[0008] S3. Perform static smoke simulation using the final test piezoelectric sheet to determine the performance stability of the photoelectric smoke fire detector under a fixed measurement concentration. Perform dynamic smoke simulation using the final test piezoelectric sheet to determine the performance stability of the photoelectric smoke fire detector under a sudden change in measurement concentration.

[0009] Since the piezoelectric film can accurately control the scattered light intensity, and the scattered light intensity can reflect the light absorption effect of smoke of different concentrations, the piezoelectric film is used instead of real smoke. By adjusting the optical properties of the piezoelectric film to simulate smoke of different concentrations, controllable test conditions are provided in the laboratory environment. The test conditions are highly repeatable, stable, and there is no need to generate actual smoke, which is more environmentally friendly and safe. By performing static smoke simulation and dynamic smoke simulation on the final test piezoelectric film, the response capability and sensitivity of the photoelectric smoke fire detector to be tested are tested from both static and dynamic perspectives, which improves the comprehensiveness of the test. Therefore, the test results can more accurately reflect whether the photoelectric smoke fire detector to be tested needs to be repaired or replaced.

[0010] Preferably, the shape of the piezoelectric sheet is changed by changing the voltage applied to each piezoelectric sheet to be selected, thereby obtaining a data matrix of sudden changes in scattered light intensity of the piezoelectric sheet to be selected;

[0011] By collecting the smoke concentration mutation data set and the scattered light intensity mutation data matrix of the candidate piezoelectric sheets, screening data support is provided for the subsequent screening of piezoelectric sheets in the candidate piezoelectric sheet set.

[0012] Preferably, said S2 comprises the following steps:

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

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

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

[0016] S211, collecting multiple sets of historical data on parameter effects of changing the scattered light intensity of the piezoelectric piece on the response speed, scattered light intensity data before the mutation, scattered light intensity data after the mutation, and mutation time data to construct a piezoelectric piece response time mapping model; adjusting the parameters of the candidate piezoelectric piece corresponding to the error data in S21 according to the piezoelectric piece response time mapping model to obtain a final test piezoelectric piece;

[0017] By setting several parameters that affect the response speed of the piezoelectric piece, the adjustment object for adjusting the response speed of the piezoelectric piece is determined; by constructing a piezoelectric piece response time mapping model, when the parameters of the initial test piezoelectric piece are adjusted later, the corresponding response time data can be mapped out in time, so as to know the effect of the parameter adjustment and make subsequent adjustments, thereby improving the adjustment efficiency and feasibility.

[0018] Preferably, the piezoelectric piece response time-consuming mapping model in S211 adopts an SVM model;

[0019] The SVM (support vector machine) model can map data from low-dimensional space to high-dimensional space and construct a linear classifier in the high-dimensional space, thereby solving the problem of nonlinear separability; the training process is relatively stable and not prone to local excellence, thereby improving the stability and reliability of the model; it is relatively robust to noisy data, that is, it is less sensitive to outliers and noise points; it has strong interpretability, and it performs classification by finding an optimal hyperplane. The position and direction of this hyperplane can be intuitively understood as the classification boundary of the data.

[0020] Preferably, the parameters in S211 are adjusted using a tuna optimization algorithm;

[0021] The tuna optimization algorithm adopts two strategies: spiral foraging and parabolic foraging, which can quickly locate potential optimal solutions in the search space. The spiral foraging strategy enables individuals to explore extensively in the search space, increasing the probability of finding the global optimal solution. It is insensitive to the choice of initial population and has relatively low requirements for parameter settings. Small changes in parameters usually do not have a significant impact on the performance of the algorithm. Based on the above advantages, the tuna optimization algorithm is used in this scheme to perform multiple iterations on multiple parameters of the piezoelectric piece at the same time, and the error between the mutation time of the piezoelectric piece and the mutation time of the actual smoke is used as the fitness function. Therefore, as the iteration proceeds, the error between the mutation time of the piezoelectric piece and the mutation time of the actual smoke becomes smaller and smaller, ultimately meeting the simulation requirements.

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

[0023] S31, using the photoelectric smoke detector to be tested to repeatedly collect light intensity data from the final test piezoelectric piece performing static smoke simulation to obtain a fixed light intensity data matrix;

[0024] S32, performing maintenance and replacement warning and alarm for the photoelectric smoke fire detector to be tested in combination with the fixed light receiving intensity data matrix;

[0025] S33. When the photoelectric smoke fire detector under test does not perform maintenance, replacement, warning, or alarm, the photoelectric smoke fire detector under test is used to repeatedly collect light intensity data on the final test piezoelectric piece performing dynamic smoke simulation to obtain a dynamic light intensity data matrix.

[0026] S34, performing maintenance and replacement warnings and alarms for the photoelectric smoke detector to be tested again based on the dynamic light intensity data set;

[0027] Since the actual smoke concentration value is constantly changing, and the scattered light intensity caused by the change of the piezoelectric piece structure needs to be dynamically controlled if it is to change dynamically, based on this, this solution performs static smoke simulation and dynamic smoke simulation on the final test piezoelectric piece, and tests the response ability and sensitivity of the photoelectric smoke fire detector to be tested from both static and dynamic perspectives, thereby improving the comprehensiveness of the test. Therefore, the test results can more accurately reflect whether the photoelectric smoke fire detector to be tested needs to be repaired and replaced.

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

[0029] S321, calculating the standard deviation of each row of data in the fixed received light intensity data matrix to obtain a current received light intensity standard deviation data set;

[0030] When the current received light intensity standard deviation data set contains current received light intensity standard deviation data that is greater than or equal to the first received light intensity discrete threshold, an alarm signal is issued; when the current received light intensity standard deviation data set only contains current received light intensity standard deviation data 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 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 the current received light intensity standard deviation data set does not contain current received light intensity standard deviation data that is greater than or equal to the second received light intensity discrete threshold, repeat S31 and S32;

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

[0032] S323, setting a first time difference threshold and a second time difference threshold;

[0033] When there is future light receiving intensity standard deviation data in the future light receiving intensity standard deviation data set that is greater than or equal to the first light receiving intensity discrete threshold, the future moment corresponding to the future light receiving intensity standard deviation data is recorded as the first future moment; when the difference between the first future moment and the present moment is greater than or equal to the first moment difference threshold, a first-level warning is issued; when the difference between the first future moment and the present moment is less than the first moment difference threshold and greater than or equal to the second moment difference threshold, a second-level warning is issued; when the difference between the first future moment and the present moment is less than the second moment difference threshold, a third-level warning is issued;

[0034] The first-level warning is used for reminders, the second-level warning is used to prepare for maintenance or replacement, and the third-level warning is used for early maintenance and replacement. By determining whether to alarm based on the degree of error between the detection data of the photoelectric smoke fire detector to be tested and the actually set data, maintenance personnel can be reminded in time to perform repairs and replacements, thereby ensuring that the photoelectric smoke fire detector to be tested can work normally. In addition, by collecting the error between the detection data of the photoelectric smoke fire detector to be tested and the actually set data multiple times, the error data at future times is predicted, so that whether the photoelectric smoke fire detector to be tested has a tendency to fail and the future time of failure can be known in advance, thereby facilitating different degrees of warnings, and then taking corresponding measures in advance to deal with it.

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

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

[0037] S342. Predict the pre-mutation received light intensity data and the post-mutation received light intensity data for future time points based on the dynamic received light intensity data matrix, and calculate the standard deviation of the pre-mutation received light intensity data and the post-mutation received light intensity data for each future time point. When any standard deviation data is greater than or equal to a first received light intensity discrete threshold, if the difference between the future time point and the current time point corresponding to the received light intensity standard deviation data is greater than or equal to the first time difference threshold, issue a first-level warning; if the difference is less than the first time difference threshold and greater than or equal to the second time difference threshold, issue a second-level warning; if the difference is less than the second time difference threshold, issue a third-level warning.

[0038] By dynamically setting the scattered light intensity caused by changes in the piezoelectric film structure, the response ability of the photoelectric smoke fire detector to smoke with a sudden change in concentration can be tested. By calculating the standard deviation of multiple detection results of the photoelectric smoke fire detector under the same conditions, it can be determined whether the detection result of the photoelectric smoke fire detector is stable. If it is unstable, that is, the calculated standard deviation data exceeds the first discrete threshold value of the received light intensity, it can be reflected that the performance of its light-emitting tube or receiving tube has changed or the circuit may have failed, and an alarm is issued to promptly remind relevant personnel to repair or replace it. In addition, if the calculated standard deviation data does not exceed the first discrete threshold value of the received light intensity, the received light intensity data at a future moment is predicted and the standard deviation is calculated. Then, according to the difference between the moment when the first discrete threshold value of the received light intensity is reached in the future and the present moment, different degrees of warning are issued to remind relevant personnel to take corresponding measures, thereby ensuring the normal operation of the photoelectric smoke fire detector.

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

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

[0041] 1. In the present invention, static smoke simulation and dynamic smoke simulation are performed on the final test piezoelectric piece to test the response capability and sensitivity of the photoelectric smoke fire detector to be tested from both static and dynamic perspectives, thereby improving the comprehensiveness of the test. Therefore, the test results can more accurately reflect whether the photoelectric smoke fire detector to be tested needs to be repaired or replaced.

[0042] 2. The present invention takes into account the response time of the structural changes of the piezoelectric film to better simulate the actual smoke concentration; by screening and adjusting relevant parameters, the response time of the corresponding piezoelectric film meets the actual simulation requirements.

[0043] 3. In the present invention, a piezoelectric piece response time mapping model is constructed, so that when the parameters of the initial test piezoelectric piece are adjusted later, the corresponding response time data can be mapped out in time, so as to know the effect of the parameter adjustment and make subsequent adjustments, thereby improving the adjustment efficiency and feasibility.

[0044] 4. The present invention employs the tuna optimization algorithm to perform multiple iterations simultaneously on multiple parameters of the piezoelectric element, and uses the error between the mutation time of the piezoelectric element and the mutation time of the actual smoke as the fitness function. Therefore, as the iterations proceed, the error between the mutation time of the piezoelectric element and the mutation time of the actual smoke becomes smaller and smaller, ultimately meeting the simulation requirements.

[0045] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions of the embodiments of the invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

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

[0048] Figure 2 Schematic diagram of the process of the photoelectric smoke fire detector detection method based on piezoelectric piece adjustment of the present invention;

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

[0050] Figure 4 This is a schematic diagram of the process of performing static performance testing on a photoelectric smoke fire detector to be tested according to the present invention;

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

[0052] Figure 6 The diagram is a module diagram of the photoelectric smoke fire detector detection system based on piezoelectric piece adjustment according to the present invention. DETAILED DESCRIPTION

[0053] The following will clearly and completely describe the technical solutions in the embodiments of the invention in conjunction with the accompanying drawings. Obviously, the embodiments described are only part of the embodiments of the invention, not all of them. All other embodiments derived by persons of ordinary skill in the art based on the embodiments of the invention without inventive effort are within the scope of protection of the invention.

[0054] Example 1

[0055] See also Figure 1-5This embodiment is a detection method for a photoelectric smoke fire detector based on piezoelectric sheet adjustment, comprising the following steps:

[0056] S1. Collecting several sets of smoke concentration change data corresponding to sudden concentration changes and scattered light intensity sudden changes caused by structural changes of several selected piezoelectric sheets, to obtain a smoke concentration sudden change data set and a matrix of scattered light intensity sudden changes of the selected piezoelectric sheets;

[0057] Said S1 comprises the following steps:

[0058] S11, set a number of piezoelectric sheets to be selected to obtain a set of piezoelectric sheets to be selected; use a concentration sensor to collect a number of groups of smoke concentration change data corresponding to sudden concentration changes to obtain a smoke concentration sudden change data set 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 They represent the concentration values of the smoke sample group i before and after the mutation and the mutation time data, and a′ represents the total number of smoke sample data groups collected;

[0061] S12. Using the smoke concentration mutation dataset and the candidate piezoelectric patch set, under the same other conditions, by changing the voltage applied to each candidate piezoelectric patch to change the shape of the piezoelectric patch, thereby changing the corresponding scattered light intensity, simulates smoke concentration data for each concentration mutation, and obtains a candidate piezoelectric patch scattered light intensity mutation data matrix;

[0062] S2. Parameter data on changing the applied voltage of the piezoelectric patch to change the response speed of the structure, data on scattered light intensity before the mutation, data on scattered light intensity after the mutation, and data on the time required for the mutation are collected to construct a piezoelectric patch response time mapping model. The Euclidean distance between the candidate piezoelectric patch scattered light intensity mutation data matrix and the smoke concentration mutation data set is calculated, and the parameters of the corresponding candidate piezoelectric patch are adjusted in combination with the piezoelectric patch response time mapping model to obtain the final test piezoelectric patch.

[0063] The S2 comprises the following steps:

[0064] S21, calculate the Euclidean distance between the time-consuming data in each row of the data matrix of the sudden change of scattered light intensity of the selected piezoelectric piece and the time-consuming data in the sudden change data set of smoke concentration, and obtain the time-consuming Euclidean distance data set represents the Euclidean distance between the time-consuming data in the jth data in the data matrix of the scattered light intensity mutation of the candidate piezoelectric piece and the time-consuming data in the smoke concentration mutation data set, Indicates the total number of piezoelectric sheets to be selected; the calculation formula is as follows:

[0065]

[0066] S22, setting a response time error threshold; when the minimum time-consuming Euclidean distance data in the time-consuming Euclidean distance data set is less than the response time error threshold, selecting the candidate piezoelectric sheet corresponding to the minimum time-consuming Euclidean distance data as the final test piezoelectric sheet; otherwise, adjusting the parameters of the candidate piezoelectric sheet corresponding to the minimum time-consuming Euclidean distance data to obtain the final test piezoelectric sheet;

[0067] In S22, adjusting the parameters of the candidate piezoelectric piece corresponding to the minimum time-consuming Euclidean distance data includes the following steps:

[0068] S221. Setting several parameters that affect the response speed of the piezoelectric piece's structural change, obtaining a set of piezoelectric piece response speed-influencing parameter types; the set of piezoelectric piece response speed-influencing parameter types includes a piezoelectric coefficient, an elastic modulus, a density, and the frequency and amplitude of a driving voltage; and collecting multiple sets of historical response speed-influencing parameter data, pre-mutation scattered light intensity data, post-mutation scattered light intensity data, and mutation time data, for changing the applied voltage of the piezoelectric piece to change the scattered light intensity, to obtain a historical response speed-influencing parameter data matrix, a historical pre-mutation scattered light intensity data set, a historical post-mutation scattered light intensity data set, and a historical mutation time data set.

[0069] S222, constructing a piezoelectric piece response time-consuming mapping model using the historical response speed influencing parameter data matrix, the historical pre-mutation scattered light intensity data set, the historical post-mutation scattered light intensity data set, and the historical mutation time-consuming data set;

[0070] The S222 includes the following steps:

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

[0072] S2222. Setting a training error threshold; inputting the historical response speed influencing parameter training data matrix, the historical pre-mutation scattered light intensity training data set, the historical post-mutation scattered light intensity training data set as training data, and the historical mutation time-consuming training data set as training labels into an initial SVM model for training; during the training process, if the training error is less than the training error threshold, stopping the training to obtain a trained SVM model; otherwise, continuing the training until the training error is less than the training error threshold;

[0073] S2223, setting a test accuracy threshold; inputting the historical response speed influencing parameter test data matrix, the historical mutation pre-scattered light intensity test data set, the historical mutation post-scattered light intensity test data set as test data, and the historical mutation time-consuming test data set as test labels into the trained SVM model for testing; after the test is completed, obtaining test accuracy data; when the test accuracy data is greater than or equal to the test accuracy threshold, using the trained SVM model as the piezoelectric piece response time-consuming mapping model; otherwise, returning 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, recording the candidate piezoelectric sheet corresponding to the minimum time-consuming Euclidean distance data in the time-consuming Euclidean distance data set as the initial test piezoelectric sheet; adjusting the parameters of the initial test piezoelectric sheet in accordance with the piezoelectric sheet response speed influencing parameter type set and the piezoelectric sheet response time-consuming mapping model, and obtaining a final test piezoelectric sheet after the adjustment is completed;

[0075] In S223, adjusting the parameters of the initial test piezoelectric piece in conjunction with the piezoelectric piece response speed influencing parameter type set and the piezoelectric piece response time-consuming mapping model includes the following steps:

[0076] S2231, obtaining the value intervals of various types of parameter data of the initial test piezoelectric sheet according to the piezoelectric sheet response speed influencing parameter type set, and obtaining the test piezoelectric sheet parameter value interval set b; as follows,

[0077]

[0078] in, represents the lower limit and upper limit of the parameter of the i-th type of the initially tested piezoelectric sheet, respectively; b′ represents the total number of parameters that have an impact on the response speed of the piezoelectric sheet;

[0079] Construct a piezoelectric piece response speed parameter to adjust the tuna population; set the maximum number of iterations of the piezoelectric piece response speed parameter to adjust the tuna population And the current number of iterations is are respectively recorded as the maximum number of iterations of response adjustment and the current number of iterations of response adjustment; the dimension of the search space for adjusting the tuna population by the piezoelectric piece response speed parameter is the same as b′; S2232, setting the initial position of each tuna in the tuna population by adjusting the piezoelectric piece response speed parameter according to the test piezoelectric piece parameter value interval set, to obtain a first initial position matrix;

[0080] The generation formula is as follows,

[0081]

[0082] Where, represents the position component of the initial position of the jth tuna in the tuna population adjusted by the piezoelectric patch response speed parameter on the parameter dimension of the i-th type of the initial test piezoelectric patch, c represents the scale of the tuna population adjusted by the piezoelectric patch response speed parameter, rand 1ji Indicates that Generate a random number between 0 and 1;

[0083] S2233, setting the piezoelectric piece response speed parameter to adjust the fitness function c1′ of the tuna population; as follows,

[0084]

[0085] Where, It represents the Euclidean distance between the response time dataset and the time data in the smoke concentration mutation dataset obtained by substituting the scattered light intensity data before and after the mutation in the candidate piezoelectric plate scattered light intensity mutation data matrix corresponding to a set of piezoelectric plate response speed parameters updated in each round of iteration and the minimum time-consuming Euclidean distance data in the time-consuming Euclidean distance dataset into the piezoelectric plate response time mapping model;

[0086] S2234. Start iteration. Before the iteration, set the current iteration number of the response adjustment to 1. During the first iteration, adjust the fitness function c1′ of the tuna population using the piezoelectric piece response speed parameter to calculate the fitness value of the initial position of each tuna in the first initial position matrix to obtain a first fitness value set. Use the maximum fitness value in the first fitness value set and the corresponding initial position of the tuna as the first global optimal fitness value and the first global optimal position, respectively. Update the initial position of each tuna in the first initial position matrix according to the first global optimal fitness value and the first global optimal position. After the update is completed, increase the current iteration number of the response adjustment by 1 and enter the next iteration.

[0087] In each of the other iterations, the fitness function c1′ of the tuna population adjusted by the piezoelectric piece response speed parameter is used to calculate the fitness value of each tuna position in the tuna population adjusted by the piezoelectric piece response speed parameter, which was updated in the previous iteration, to obtain a second fitness value set; the maximum fitness value and the corresponding tuna position in the second fitness value set are respectively used as the second global optimal fitness and the second global optimal position; the position of each tuna in the tuna population adjusted by the piezoelectric piece response speed parameter, which was 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 increased by 1 and the next iteration is entered;

[0088] S2235, when When , stop the iteration and get the first final global best fitness and the first final global best position; otherwise, continue to iterate until time; using the first final global optimal fitness as the minimum optimized time-consuming Euclidean distance; when the minimum optimized time-consuming Euclidean distance is less than the response time error threshold, setting the parameters of the initial test piezoelectric sheet according to each position component of the first final global optimal position to obtain a final test piezoelectric sheet; otherwise, returning to S2234 to continue iterating until the minimum optimized time-consuming Euclidean distance is less than the response time error threshold;

[0089] S3. Perform static smoke simulation using the final test piezoelectric sheet to determine the performance stability of the photoelectric smoke fire detector under a fixed measurement concentration. Perform dynamic smoke simulation using the final test piezoelectric sheet to determine the performance stability of the photoelectric smoke fire detector under a sudden change in measurement concentration.

[0090] The S3 includes the following steps:

[0091] S31. Setting a set scattered light intensity and a photoelectric smoke detector to be tested; fixing the final test piezoelectric piece according to the set scattered light intensity and performing a static smoke simulation; then periodically and continuously collecting light intensity data on the final test piezoelectric piece undergoing the static smoke simulation using the photoelectric smoke detector to be tested, to obtain a fixed light intensity data matrix;

[0092] S32: Setting a first discrete threshold value for received light intensity and a second discrete threshold value for received light intensity; and performing a maintenance and replacement warning and an alarm for the photoelectric smoke detector to be tested based on the first discrete threshold value for received light intensity, the second discrete threshold value for received light intensity, and the fixed received light intensity data matrix.

[0093] The S32 includes the following steps:

[0094] S321, calculating the standard deviation of each row of data in the fixed received light intensity data matrix to obtain a current received light intensity standard deviation data set;

[0095] When the current received light intensity standard deviation data set contains current received light intensity standard deviation data that is greater than or equal to the first received light intensity discrete threshold, an alarm signal is issued; when the current received light intensity standard deviation data set only contains current received light intensity standard deviation data 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 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 the current received light intensity standard deviation data set does not contain current received light intensity standard deviation data that is greater than or equal to the second received light intensity discrete threshold, repeat S31 and S32;

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

[0097] S323, setting a first time difference threshold and a second time difference threshold;

[0098] When there is future light receiving intensity standard deviation data in the future light receiving intensity standard deviation data set that is greater than or equal to the first light receiving intensity discrete threshold, the future moment corresponding to the future light receiving intensity standard deviation data is recorded as the first future moment; when the difference between the first future moment and the present moment is greater than or equal to the first moment difference threshold, a first-level warning is issued; when the difference between the first future moment and the present moment is less than the first moment difference threshold and greater than or equal to the second moment difference threshold, a second-level warning is issued; when the difference between the first future moment and the present moment is less than the second moment difference threshold, a third-level warning is issued;

[0099] S33. When the photoelectric smoke fire detector under test does not perform a maintenance replacement warning or an alarm, setting a pre-set mutation front scattered light intensity and a pre-set mutation rear scattered light intensity; performing a dynamic smoke simulation on the final test piezoelectric piece based on the pre-set mutation front scattered light intensity and the pre-set mutation rear scattered light intensity; and then periodically collecting light receiving intensity data of the final test piezoelectric piece undergoing the dynamic smoke simulation multiple times using the photoelectric smoke fire detector under test to obtain a dynamic light receiving intensity data matrix;

[0100] S34, setting a maintenance and replacement warning and an alarm for the photoelectric smoke detector to be tested again based on the first light receiving intensity discrete threshold, the second light receiving intensity discrete threshold, and the dynamic light receiving intensity data set;

[0101] The S34 includes the following steps:

[0102] S341, calculating 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 data set, to obtain a light intensity standard deviation data set before the current mutation and a light intensity standard deviation data set after the current mutation;

[0103] When the standard deviation data set of the current light receiving intensity before the mutation or the standard deviation data set of the light receiving intensity after the mutation exists and is greater than or equal to the first light receiving intensity discrete threshold, an alarm signal is issued; when the standard deviation data set of the current light receiving intensity before the mutation or the standard deviation data set of the light receiving intensity after the mutation only exists and is less than the first light receiving intensity discrete threshold and greater than or equal to the second light receiving intensity discrete threshold, the standard deviation data set of the current light receiving intensity before the mutation and the standard deviation data set of the light receiving intensity after the mutation are used as the current standard deviation data set of the light receiving intensity before the mutation and the current standard deviation data set of the light receiving intensity after the mutation, respectively, and enter S342; if the standard deviation data set of the current light receiving intensity before the mutation or the standard deviation data set of the light receiving intensity after the mutation does not exist and is greater than or equal to the second light receiving intensity discrete threshold, repeat S33 and S34;

[0104] S342. Set several more future time points to obtain a second set of future time points; predict the pre-mutation received light intensity data and the post-mutation received light intensity data of the future time points using a BP neural network model based on the second set of future time points and the dynamic received light intensity data matrix to obtain a future dynamic received light intensity data matrix; calculate the standard deviation of the pre-mutation received light intensity data and the post-mutation received light intensity data for each future time point in the future dynamic received light intensity data matrix to obtain a future pre-mutation received light intensity standard deviation dataset and a future post-mutation received light intensity standard deviation dataset;

[0105] S343. When the standard deviation data set of the light receiving intensity before the future mutation and the standard deviation data set of the light receiving intensity after the future mutation have standard deviation data greater than or equal to the first light receiving intensity discrete threshold, the future moment corresponding to the light receiving intensity standard deviation data is recorded as the second future moment; when the difference between the first future moment and the present moment is greater than or equal to the first moment difference threshold, a first-level warning is issued; when the difference between the first future moment and the present moment is less than the first moment difference threshold and greater than or equal to the second moment difference threshold, a second-level warning is issued; when the difference between the first future moment and the present moment is less than the second moment difference threshold, a third-level warning is issued.

[0106] Example 2

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

[0108] The smoke concentration mutation data collection module collects a number of smoke concentration change data corresponding to sudden concentration changes to obtain a smoke concentration mutation data set;

[0109] The smoke concentration mutation data set of the smoke concentration mutation data set is used to collect the scattered light intensity mutation data caused by the structural changes of the candidate piezoelectric pieces, and obtain the scattered light intensity mutation data matrix of the candidate piezoelectric pieces;

[0110] The smoke concentration mutation data set of the response time mapping model construction module collects multiple sets of historical data on the response speed of the piezoelectric plate to change the scattered light intensity by changing the applied voltage of the piezoelectric plate, the scattered light intensity data before the mutation, the scattered light intensity data after the mutation, and the mutation time data to construct the piezoelectric plate response time mapping model;

[0111] The smoke concentration mutation dataset of the candidate piezoelectric piece parameter adjustment module calculates the Euclidean distance between each row of data in the candidate piezoelectric piece scattered light intensity mutation data matrix and the smoke concentration mutation dataset, and adjusts the parameters of the corresponding candidate piezoelectric piece in combination with the piezoelectric piece response time-consuming mapping model to obtain the final test piezoelectric piece;

[0112] The smoke concentration mutation dataset of the static performance detection module of the photoelectric smoke fire detector is simulated by using the final test piezoelectric piece to simulate the static smoke to measure the performance stability of the smoke of the photoelectric smoke fire detector under the condition of fixed concentration;

[0113] The smoke concentration mutation dataset of the dynamic performance detection module of the photoelectric smoke fire detector uses the final test piezoelectric piece to perform dynamic smoke simulation to measure the performance stability of the smoke of the photoelectric smoke fire detector under the condition of sudden concentration changes.

[0114] Example 3

[0115] This embodiment discloses a storage medium having a program stored thereon. When the program is executed by a processor, it is used to implement the system of the above embodiment.

[0116] Throughout this specification, references to terms such as "one embodiment," "example," or "specific example" indicate that the specific features, structures, materials, or characteristics described in conjunction with that embodiment or example are included in at least one embodiment or example of the invention. In this specification, schematic representations of these 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 any one or more embodiments or examples.

[0117] The preferred embodiments of the invention disclosed above are intended only to help illustrate the invention. These preferred embodiments do not exhaust all details, nor do they limit the invention to the specific embodiments described. Obviously, many modifications and variations are possible based on the content of this specification. These embodiments are selected and described in detail in this specification 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 photoelectric smoke fire detector detection method based on piezoelectric adjustment, characterized in that: The following steps are involved: S1. Collecting several sets of smoke concentration change data corresponding to sudden concentration changes and several sets of scattered light intensity sudden change data of selected piezoelectric sheets to obtain a smoke concentration sudden change data set and a matrix of scattered light intensity sudden change data of selected piezoelectric sheets; S2, in conjunction with the data collected in S1, and by collecting historical data on the parameters affecting the response speed of the piezoelectric piece's structural change, the scattered light intensity data before the mutation, the scattered light intensity data after the mutation, and the mutation time consumption data, to build a piezoelectric piece response time consumption mapping model; and adjust the parameters of the corresponding candidate piezoelectric piece to obtain the final test piezoelectric piece; S3. Static smoke simulation is performed using the final test piezoelectric piece to measure the performance stability of the photoelectric smoke detector under fixed smoke concentration. Then, dynamic smoke simulation is performed using the final test piezoelectric piece to measure the performance stability of the smoke of the photoelectric smoke fire detector under sudden changes in the measured concentration.

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

3. The photoelectric smoke fire detector detection method based on piezoelectric piece adjustment according to claim 2 is characterized in that: The S2 comprises the following steps: S21. When the error between the scattered light intensity mutation data matrix of the candidate piezoelectric plate and the corresponding data in the smoke concentration mutation data set is less than the response time error threshold, the candidate piezoelectric plate corresponding to the error data is used as the final test piezoelectric plate; otherwise, the parameters of the candidate piezoelectric plate corresponding to the error data are adjusted until the error between the scattered light intensity mutation data matrix of the candidate piezoelectric plate and the corresponding data in the smoke concentration mutation data set is less than the response time error threshold, thereby obtaining the final test piezoelectric plate.

4. The photoelectric smoke fire detector detection method based on piezoelectric piece adjustment according to claim 3 is characterized in that: Adjusting the parameters of the selected piezoelectric piece corresponding to the error data in S21 includes the following steps: S211. Collect multiple sets of historical parameter data affecting the response speed of the piezoelectric piece's 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 piece response time mapping model; adjust the parameters of the candidate piezoelectric piece corresponding to the error data in S21 in conjunction with the piezoelectric piece response time mapping model to obtain the final test piezoelectric piece.

5. The photoelectric smoke fire detector detection method based on piezoelectric piece adjustment according to claim 4 is characterized in that: The piezoelectric piece response time-consuming mapping model described in S211 adopts the SVM model.

6. The photoelectric smoke fire detector detection method based on piezoelectric piece adjustment according to claim 5 is characterized in that: The parameters in S211 are adjusted using the tuna optimization algorithm.

7. The detection method of a photoelectric smoke fire detector based on piezoelectric sheet adjustment according to claim 6, characterized in that: The S3 includes the following steps: S31, using the photoelectric smoke detector to be tested to repeatedly collect light intensity data from the final test piezoelectric piece performing static smoke simulation to obtain a fixed light intensity data matrix; S32, performing maintenance and replacement warning and alarm for the photoelectric smoke fire detector to be tested in combination with the fixed light receiving intensity data matrix; S33. When the photoelectric smoke fire detector under test does not perform maintenance, replacement, warning, or alarm, the photoelectric smoke fire detector under test is used to repeatedly collect light intensity data on the final test piezoelectric piece performing dynamic smoke simulation to obtain a dynamic light intensity data matrix. S34. Perform maintenance and replacement warning and alarm again for the photoelectric smoke detector to be tested based on the dynamic light receiving intensity data set.

8. The photoelectric smoke fire detector detection method based on piezoelectric piece adjustment according to claim 7 is characterized in that: The S34 includes the following steps: S341: Set a first discrete threshold value for received light intensity and a second discrete threshold value for received light intensity; calculate the standard deviation of the received light intensity data before the current mutation and the received light intensity data after the current mutation in the dynamic received light intensity data set; if any standard deviation data is greater than or equal to the first discrete threshold value for received light intensity, issue an alarm signal; if only any standard deviation data is less than the first discrete threshold value for received light intensity and greater than or equal to the second discrete threshold value for received light intensity, proceed to S342; if no standard deviation data is greater than or equal to the second discrete threshold value for received light intensity, repeat S33 and S34; S342. Predict the received light intensity data before the mutation and the received light intensity data after the mutation at future time points based on the dynamic received light intensity data matrix, and calculate the standard deviation of the received light intensity data before the mutation and the received light intensity data after the mutation at each future time point; when there is standard deviation data greater than or equal to the first received light intensity discrete threshold, if the difference between the future moment and the present moment corresponding to the received light intensity standard deviation data is greater than or equal to the first moment difference threshold, a first-level warning is issued; if the difference is less than the first moment difference threshold and greater than or equal to the second moment difference threshold, a second-level warning is issued; if the difference is less than the second moment difference threshold, a third-level warning is issued.

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

10. A storage medium having a program stored thereon, wherein when the program is executed by a processor, Used to implement the photoelectric smoke fire detector detection method as described in any one of claims 1-8.

Images