A method, device, equipment and medium for detecting the state of a fire detector

Abstract

The present invention is applicable to the technical field of device detection, and particularly relates to a method, device, equipment and medium for detecting the state of a fire detector. By selecting a preset fitting method according to the environmental state, the present invention respectively fits N initial detection values and K sets of initial detection values, and uses the obtained first target detection function and multiple second target detection functions to evaluate the reliability of the target fire detector. Considering from multiple perspectives of the whole and the local, the accuracy of the reliability evaluation is improved by mutual verification of multiple functions. By comprehensively considering multiple factors such as the comprehensive reliability, the second reference detection value curve corresponding to the environmental state, the initial detection value and the first target detection function, etc., the abnormal detection value is determined and the state monitoring result of the target fire detector is determined. Constraining and judging the initial detection value from different factors and aspects improves the screening accuracy of the abnormal detection value, and further improves the accuracy of the state detection result of the target fire detector.

Description

Technical Field

[0001] The present invention is applicable to the technical field of device detection, and particularly relates to a method, device, equipment and medium for detecting the state of a fire detector. Background Art

[0002] In the prior art, the methods for detecting the state of a fire detector include a hardware self-checking method, a manual inspection method and a communication detection method.

[0003] The hardware self-checking method performs self-detection through a built-in simple circuit, and can only detect obvious hardware damages such as whether the power supply is normal and whether the sensor can respond to basic information. It is difficult to detect subtle performance declines such as the gradual decrease in the sensitivity of the sensor. The manual inspection method detects the state by arranging staff to regularly check the appearance and perform function tests on the fire detector. This not only consumes a large amount of manpower and time costs, but also makes it difficult to detect in time when a fire detector suddenly fails between two inspection cycles, and it is impossible to detect hidden faults in the internal software algorithm of the fire detector, resulting in a significant reduction in the reliability of the fire safety system.

[0004] The communication detection method can compare the detection data such as the smoke concentration and temperature value returned by the fire detector with a preset fixed threshold. If the detection data exceeds the threshold range, it is determined that the fire detector has a fault, or the current data returned by the fire detector is simply compared with the historical data of a past period of time. If the current data deviates greatly from the historical data, it is determined that the fire detector has a fault. However, the above communication detection method does not consider the decrease in the reliability of the detection data caused by factors such as equipment aging, resulting in missed judgments or misjudgments of faults, making it impossible to accurately and efficiently judge the true working state of the fire detector and reducing the reliability and stability of the fire detection system.

[0005] Therefore, when detecting the state of a fire detector, how to improve the accuracy of the detection result has become an urgent problem to be solved. Summary of the Invention

[0006] In view of this, embodiments of the present invention provide a method, device, equipment and medium for detecting the state of a fire detector to solve the problem of low accuracy of the detection result of the state of the fire detector.

[0007] In a first aspect, an embodiment of the present invention provides a method for detecting the state of a fire detector, and the method for detecting the state of the fire detector includes:

[0008] Obtain N initial detection values corresponding to a target fire detector at N preset time points, and divide the N initial detection values into K initial detection value sets, where N and K are both integers greater than 1.

[0009] Based on the first reference detection value curve corresponding to the location of the target fire detector and N initial detection values, obtain the environmental state corresponding to the location of the target fire detector, where the environmental state is a normal state or a fire state.

[0010] According to the preset fitting method corresponding to the environmental state, respectively fit the N initial detection values and K initial detection value sets to obtain the first target detection function corresponding to the N initial detection values for the target fire detector, and the second target detection function corresponding to each initial detection value set.

[0011] Based on the first target detection function and K second target detection functions, obtain the reliability level corresponding to the target fire detector.

[0012] According to the reliability level, the second reference detection value curve corresponding to the environmental state, the N initial detection values, and the first target detection function, obtain several abnormal detection values corresponding to the target fire detector.

[0013] Based on all the abnormal detection values, obtain the detection state corresponding to the target fire detector.

[0014] In a second aspect, an embodiment of the present invention provides a state detection device for a fire detector. The state detection device for the fire detector includes:

[0015] A data acquisition module, configured to acquire N initial detection values corresponding to the target fire detector at N preset time points, and divide the N initial detection values into K initial detection value sets, where both N and K are integers greater than 1.

[0016] An environmental state judgment module, configured to obtain the environmental state corresponding to the location of the target fire detector according to the first reference detection value curve corresponding to the location of the target fire detector and the N initial detection values, where the environmental state is a normal state or a fire state.

[0017] A detection function fitting module, configured to respectively fit the N initial detection values and the K initial detection value sets according to the preset fitting method corresponding to the environmental state, to obtain the first target detection function corresponding to the N initial detection values for the target fire detector, and the second target detection function corresponding to each initial detection value set.

[0018] A reliability level analysis module, configured to obtain the reliability level corresponding to the target fire detector according to the first target detection function and the K second target detection functions.

[0019] An abnormal detection value screening module, configured to obtain a plurality of abnormal detection values corresponding to a target fire detector according to a reliability level, a second reference detection value curve corresponding to an environmental state, N initial detection values, and a first target detection function.

[0020] A detection status acquisition module, configured to obtain a detection status corresponding to the target fire detector according to all the abnormal detection values.

[0021] In a third aspect, an embodiment of the present invention provides a computer device, which includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the state detection method of the fire detector as described in the first aspect is implemented.

[0022] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the state detection method of the fire detector as described in the first aspect is implemented.

[0023] The beneficial effects of the embodiments of the present invention compared with the prior art are as follows: By selecting a preset fitting method according to the environmental state, the N initial detection values and the K initial detection value sets are respectively fitted to obtain a first target detection function to perform an overall feature analysis on the detection data, and a second target detection function to perform a local feature analysis on the detection data, which can better adapt to the data characteristics in different dimensions, and the targeted fitting method can more accurately describe the data change trend, improving the characterization accuracy of the working state of the target fire detector; Using the first target detection function and multiple second target detection functions to evaluate the reliability level of the target fire detector, considering comprehensively from multiple perspectives of the whole and the local, and avoiding the limitations of single-function evaluation through mutual verification of multiple functions, improving the evaluation accuracy of the reliability level; Determining the abnormal detection values by comprehensively considering multiple factors such as the reliability level, the second reference detection value curve corresponding to the environmental state, the initial detection values, and the first target detection function, constraining and judging the initial detection values from different factors and aspects, improving the screening accuracy of the abnormal detection values, and being able to more comprehensively identify real abnormal situations; Finally, determining the detection status of the target fire detector according to all the abnormal detection values, improving the accuracy of the detection result of the state of the target fire detector, and providing clear guidance for the operation and maintenance of the target fire detector. Description of the Drawings

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments or the description of the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0025] Figure 1 It is a schematic diagram of an application environment of a method for detecting the state of a fire detector provided in the first embodiment of the present invention;

[0026] Figure 2 It is a schematic flowchart of a method for detecting the state of a fire detector provided in the first embodiment of the present invention;

[0027] Figure 3 It is a schematic structural diagram of a device for detecting the state of a fire detector provided in the second embodiment of the present invention;

[0028] Figure 4 It is a schematic structural diagram of a computer device provided in the third embodiment of the present invention. Detailed implementation manners

[0029] In the following description, for the purpose of illustration rather than limitation, specific details such as specific system architectures, technologies, etc. are presented to thoroughly understand the embodiments of the present invention. However, those skilled in the art should clearly understand that the present invention can also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid unnecessary details from interfering with the description of the present invention.

[0030] It should be understood that when used in the specification of the present invention and the appended claims, the term "comprising" indicates the presence of the described features, wholes, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their combinations.

[0031] It should also be understood that the term "and / or" as used in the specification of the present invention and the appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0032] As used in the specification of the present invention and the appended claims, the term "if" can be interpreted as "when...", "once", "in response to determining", or "in response to detecting" according to the context. Similarly, the phrase "if determined" or "if [the described condition or event] is detected" can be interpreted as meaning "once determined", "in response to determining", "once [the described condition or event] is detected", or "in response to detecting [the described condition or event]" according to the context.

[0033] In addition, in the description of the specification of the present invention and the appended claims, the terms "first", "second", "third", etc. are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance.

[0034] References to "one embodiment" or "some embodiments" or the like described in the specification of the present invention mean that a particular feature, structure, or characteristic described in connection with that embodiment is included in one or more embodiments of the present invention. Thus, statements such as "in one embodiment", "in some embodiments", "in other some embodiments", "in still other embodiments", etc., which appear in different places in this specification, do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized. The terms "comprising", "including", "having" and their variants mean "including but not limited to", unless otherwise specifically emphasized.

[0035] The embodiments of the present invention can acquire and process relevant data based on artificial intelligence technology. Among them, artificial intelligence (AI) is a theory, method, technology, and application system that uses a digital computer or a machine controlled by a digital computer to simulate, extend, and expand human intelligence, perceive the environment, acquire knowledge, and use knowledge to obtain the best results.

[0036] Artificial intelligence basic technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation / interaction systems, and mechatronics. Artificial intelligence software technologies mainly include several major directions such as computer vision technology, robotics, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0037] It should be understood that the magnitudes of the sequence numbers of the steps in the following embodiments do not mean the order of execution is prior or subsequent. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

[0038] In order to illustrate the technical solutions of the present invention, specific embodiments will be used for illustration below.

[0039] A method for detecting the state of a fire detector provided in the first embodiment of the present invention can be applied in an application environment such as Figure 1 where the client communicates with the server. Among them, the client includes but is not limited to computer devices such as a palm computer, a desktop computer, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook, a cloud computer device, and a personal digital assistant (PDA). The server can be implemented by an independent server or a server cluster composed of multiple servers.

[0040] See Figure 2, which is a schematic flowchart of a method for detecting the state of a fire detector provided in the first embodiment of the present invention. The above method for detecting the state of a fire detector can be applied to Figure 1 the client in

[0041] S1. Obtain N initial detection values corresponding to the target fire detector at N preset time points, and divide the N initial detection values into K initial detection value sets, where both N and K are integers greater than 1.

[0042] Among them, in a large building or area, multiple fire detectors may be installed. The target fire detector is a specific fire detector whose state is monitored and analyzed in the fire detection system.

[0043] The preset time points are a series of pre-set time nodes, which can be evenly distributed at a certain time interval or flexibly set according to actual detection requirements. For example, the time points can be encrypted during high fire incidence periods.

[0044] Obtaining the detection values corresponding to the target fire detector at each preset time point and dividing them into K initial detection value sets helps to more carefully analyze the characteristics and laws of the initial detection values. Among them, the division method can be average grouping according to the time sequence.

[0045] Optionally, obtaining N initial detection values corresponding to the target fire detector at N preset time points and dividing the N initial detection values into K initial detection value sets includes:

[0046] S11. Obtain the identification information of the main control module, the drive module, the detection module, and the target fire detector, where the drive module and the target fire detector are respectively connected to the loop bus.

[0047] S12. Control the drive module by the main control module to output test information to the loop bus during the first preset period, where the test information includes the identification information of the target fire detector.

[0048] S13. Obtain the response information of the target fire detector from the loop bus by the detection module during the second preset period, where the response information includes N initial detection values corresponding to the target fire detector at N preset time points.

[0049] Among them, the first preset period is a pre-set time period. During the first preset period, the main control module controls the drive module to output test information to the loop bus, which limits the time range for sending test information, ensures that the system performs test operations at an appropriate time, and avoids interfering with normal fire monitoring work. The first preset period can be adjusted according to the working characteristics and actual requirements of the system.

[0050] The second preset time period is another preset time period. During the second preset time period, the detection module obtains the response information of the target fire detector from the loop bus. The second preset time period includes N preset time points, so as to obtain N initial detection values.

[0051] As described above, obtaining the initial detection values of the target fire detector at multiple preset time points and dividing them into K sets of initial detection values helps to more carefully analyze the characteristics and laws of the initial detection values, providing a data basis for further analyzing the working state and environmental state of the target fire detector.

[0052] S2. According to the first reference detection value curve corresponding to the location of the target fire detector and the N initial detection values, obtain the environmental state corresponding to the location of the target fire detector, where the environmental state is a normal state or a fire state.

[0053] Among them, the first reference detection value curve is a curve drawn based on the historical detection data corresponding to the normal environmental state of the location of the target fire detector. These historical detection data record the variation of the normal detection values at this location at different times. For example, the normal fluctuation ranges of parameters such as temperature, humidity, and smoke concentration at different time periods within a day. By statistically analyzing and fitting a large amount of historical data, the first reference detection value curve can be obtained, which serves as an important reference basis for judging the current environmental state.

[0054] Compare and analyze the first reference detection value curve corresponding to the location of the target fire detector with the N initial detection values obtained. Since the first reference detection value curve represents the variation trend of the detection values under normal conditions at this location, and the initial detection value is the current actual detection result, if the deviation between the initial detection value and the reference detection value curve is within a reasonable range, it indicates that the variation of the current environmental parameters conforms to the normal situation, and it can be judged that the location of the target fire detector is in a normal state. On the contrary, if there is a large deviation between the initial detection value and the reference detection value curve, exceeding the normal fluctuation range, such as a sharp rise in the detected temperature or a sudden increase in the smoke concentration, it can be judged that this location is in a fire state.

[0055] As described above, combining the first reference detection value curve and the current initial detection value to judge the environmental state fully considers the historical environmental characteristics of this location, avoids misjudgment that may be caused by a single threshold judgment, and can adapt to various environmental changes such as different places and different seasons, improving the reliability of the state detection result.

[0056] S3. Fit the N initial detection values and the K initial detection value sets respectively according to the preset fitting method corresponding to the environmental state, to obtain the first target detection function corresponding to the N initial detection values for the target fire detector, and the second target detection function corresponding to each initial detection value set.

[0057] Among them, the preset fitting method is a method preset for fitting detection value data. Different fitting methods will be adopted according to different environmental states, which helps to more clearly understand the differences in the change trends of the detection values of the fire detector under different working states and environmental parameters, and provides a more reliable basis for accurately judging the reliability of the detector and detecting abnormal values subsequently.

[0058] The first target detection function is a function obtained by fitting the N initial detection values using the preset fitting method corresponding to the environmental state, which can overall describe the change trend of the detection values of the target fire detector at multiple time points and reflect the comprehensive working conditions of the target fire detector.

[0059] The second target detection function is a function obtained by fitting each initial detection value set using the preset fitting method corresponding to the environmental state. Each second target detection function describes the change law of the data within a specific set and can more deeply analyze the characteristics of different parts of the data.

[0060] As described above, selecting different preset fitting methods according to different environmental states to fit the data to deeply explore the data change laws of the N initial detection values and each initial detection value set can be more in line with the actual situation, specifically capture the differences in the change trends of the detection values, and provide a more reliable basis for accurately judging the reliability of the target fire detector and detecting abnormal values subsequently.

[0061] Optionally, fitting the N initial detection values and the K initial detection value sets respectively according to the preset fitting method corresponding to the environmental state, to obtain the first target detection function corresponding to the N initial detection values for the target fire detector, and the second target detection function corresponding to each initial detection value set, includes:

[0062] S31. Fit the N initial detection values with an m - degree polynomial to obtain the first reference detection function corresponding to the target fire detector and the first gradient set corresponding to the first reference detection function, where m is an integer greater than 1, and the first gradient set includes the first gradient values corresponding to N preset time points.

[0063] S32, update m = m - 1, and return to execute the step of fitting the N initial detection values with a polynomial of degree m to obtain the first reference detection function corresponding to the target fire detector and the first gradient set corresponding to the first reference detection function, until the first gradient set meets the first preset condition corresponding to the environmental state or the updated m meets the second preset condition. Determine the first reference detection function corresponding to the condition as the first target detection function corresponding to the target fire detector, and determine the degree of the first target detection function as the reference degree c, where c is an integer greater than 0.

[0064] S33, for any initial detection value set, fit the current initial detection value set with a polynomial of degree c to obtain the second reference detection function corresponding to the target fire detector for the current initial detection value set and the second gradient set corresponding to the second reference detection function, where the number of gradient values in the second gradient set corresponding to the current initial detection value set is the same as the number of initial detection values in the current initial detection value set.

[0065] S34, update c = c - 1, and return to execute the step of fitting the current initial detection value set with a polynomial of degree c to obtain the second reference detection function corresponding to the target fire detector for the current initial detection value set and the second gradient set corresponding to the second reference detection function, until the second gradient set meets the first preset condition corresponding to the environmental state or the updated c meets the second preset condition. Determine the second reference detection function corresponding to the condition as the second target detection function corresponding to the target fire detector for the current initial detection value set.

[0066] S35, traverse all the initial detection value sets to obtain the second target detection function corresponding to the target fire detector for each initial detection value set.

[0067] Among them, the polynomial of degree m refers to the mathematical expression in the form of y = a 0 + a 1 × x + a 2 × x 2 + …… + a m × x m where a 0 、a 1 、a 2 、……、a m are coefficients, x is the independent variable, y is the dependent variable, m is the degree of the polynomial, and m is an integer greater than 1. In this step, x can represent time, y can represent the detection value of the target fire detector at the corresponding time, and the polynomial of degree m is used to fit the N initial detection values. By mathematical calculation, a suitable polynomial function of degree m is found to make it as close as possible to these N data points, so as to obtain the first reference detection function.

[0068] As m changes and the fitting operation is repeatedly executed, the first reference detection function is continuously adjusted. Eventually, a suitable first reference detection function is selected as the first target detection function through preset conditions.

[0069] The first gradient set contains first gradient values corresponding to N preset time points. The gradient value represents the rate of change of a function at a certain point. Therefore, the first gradient set reflects the change situation of the first reference detection function at each preset time point, and thus is used to characterize the detection situation of the target fire detector for the environment.

[0070] The first preset condition is a judgment condition preset according to the environmental state, and is used to judge whether the first gradient set meets the requirements. The second preset condition is used to judge whether the updated m meets the requirements.

[0071] The reference number c is the number corresponding to the first target detection function, and is subsequently used as the degree basis of the polynomial for fitting each initial detection value set.

[0072] After fitting each initial detection value set with a polynomial of degree c, a second reference detection function is obtained. As c continuously changes and the fitting operation is repeatedly executed, the second reference detection function is continuously adjusted. Eventually, a suitable second reference detection function is selected as the second target detection function through preset conditions.

[0073] The second gradient set corresponds to the second reference detection function. The number of gradient values in the second gradient set is the same as the number of initial detection values in the corresponding initial detection value set, and reflects the change situation of the second reference detection function at the time points corresponding to the current initial detection value set.

[0074] As described above, by continuously adjusting the degree of the polynomial and determining the final target detection function according to whether the first gradient set, the second gradient set, and the degree of the polynomial meet the preset conditions, it is possible to adaptively find the fitting function most suitable for the data characteristics, so that the first target detection function can more accurately reflect the working state of the target fire detector as a whole, while the second target detection function can help discover local features and abnormal situations in the detection data. Moreover, different environmental states and data distributions are best fitted with polynomials of different degrees, which can improve the accuracy and adaptability of fitting, and improve the accuracy and reliability in subsequent state analysis of the target fire detector.

[0075] Optionally, the first preset condition includes:

[0076] If the environmental state is a normal state, the first gradient set meeting the first preset condition corresponding to the environmental state means that there is a first gradient value in the first gradient set that is less than the first preset gradient value or greater than the second preset gradient value.

[0077] If the environmental state is a fire state, the first gradient set satisfying the first preset condition corresponding to the environmental state means that there is a first gradient value less than the third preset gradient value in the first gradient set.

[0078] The second preset condition includes:

[0079] The updated m satisfying the second preset condition means that the updated m is less than the preset polynomial degree.

[0080] Among them, in data fitting, the degree of the polynomial determines the complexity of the fitting curve. A polynomial with a higher degree can provide a more flexible curve shape and better capture the subtle changes and local features in the data. However, when the degree of the polynomial is too high, the fitting function may closely follow the data points, including some noise or abnormal fluctuations in the data, resulting in overfitting and a poor representation of the overall data trend.

[0081] When it is determined that the environmental state is a normal state, the temperature in the environment changes little. The first preset gradient value and the second preset gradient value are correspondingly set as judgment thresholds. If there is a first gradient value less than the first preset gradient value or greater than the second preset gradient value in the first gradient set, it means that the fluctuation degree of the first reference detection function obtained by fitting with the m - degree polynomial is too high, there is an overfitting situation, and it cannot well reflect the change trend of the data in the normal state and does not meet the function requirements in the normal state.

[0082] When it is determined that the environmental state is a fire state, the temperature in the environment is continuously rising. The third preset gradient value is correspondingly set as the judgment threshold. If there is a first gradient value less than the third preset gradient value in the first gradient set, it means that the change rate of the first reference detection function obtained by fitting with the m - degree polynomial is too small or negative at some time points, and it fails to accurately capture the trend of the rapid or stable rise of the temperature in the fire state, resulting in the temperature change curve presented by the fitting function not conforming to the actual temperature rise during a fire. There are abnormal values among the N initial detection values, and it is necessary to reduce the degree of analysis of local data and increase the attention to the overall data.

[0083] Therefore, by reducing the value of m to readjust the polynomial function, the first target detection function is obtained. Since reducing m is equivalent to reducing the number of parameters in the fitting function and restricting the flexibility of the function, the function is more inclined to capture the main trend in the data rather than fitting every detail, thereby balancing the overall representation and detail analysis of the first target detection function for the N initial detection values and improving the representation accuracy on the basis of ensuring the representation degree of the working state of the target fire detector.

[0084] Among them, the specific values of the first preset gradient value, the second preset gradient value, and the third preset gradient value can be set by the implementer according to the actual situation. For example, the first preset gradient value can be set to be less than 0, the second preset gradient value can be set to be equal to 0, and the third preset gradient value can be set to be greater than 0.

[0085] During the process of continuously updating the polynomial degree, check whether the updated polynomial degree is less than the preset polynomial degree. If the lower limit of the preset polynomial degree has been reached, stop reducing the degree for fitting, and determine the current first reference detection function as the first target detection function to reduce unnecessary calculations and improve calculation efficiency.

[0086] As described above, the characteristics of data changes in the normal state and the fire state are different. Different first preset conditions are set according to different environmental states, so that the fitting function can better adapt to different environments, can more accurately judge the effectiveness of the fitting function in different situations, and limit the adjustment range of the polynomial degree by setting the preset polynomial degree. On the basis of ensuring the representation degree of the working state of the target fire detector, the representation accuracy is improved, and thus the accuracy of subsequent state detection of the fire detector is improved.

[0087] S4. Obtain the reliability degree corresponding to the target fire detector according to the first target detection function and the K second target detection functions.

[0088] Among them, the smaller the difference between the first target detection function and the K second target detection functions, the closer the change trends of the detection values of the first target detection function and the K second target detection functions at different time points, indicating that the analysis of the environmental state changes by multiple functions is similar, that is, the change trends of multiple target detection functions can play a role in mutual verification. And multiple target detection functions are obtained under different fitting dimensions, thus characterizing the reliability degree of the detection result of the target fire detector.

[0089] Optionally, obtaining the reliability degree corresponding to the target fire detector according to the first target detection function and the K second target detection functions includes:

[0090] S41. For any second target detection function, obtain the time point range corresponding to the current second target detection function according to the preset time points corresponding to the initial detection value set corresponding to the current second target detection function.

[0091] S42. Calculate the degree of difference between the current second target detection function and the first target detection function within the time point range.

[0092] S43. Traverse the K second target detection functions to obtain the degree of difference between each second target detection function and the first target detection function.

[0093] S44. Calculate the reliability corresponding to the target fire detector according to the K degrees of difference.

[0094] Among them, the preset time points corresponding to the initial detection values used when fitting each second target detection function are combined to form a time point range as the basis for evaluating the degree of difference between each second target detection function and the first target detection function, which can improve the accuracy of the evaluation results.

[0095] For the preset time points within the time point range, calculate the output values of the first target detection function and each second target detection function respectively, and then calculate the difference between the output values, such as features like the mean absolute error and mean square error between two sets of output values, to characterize the degree of difference between each second target detection function and the first target detection function within the time point range.

[0096] Calculate the reliability corresponding to the target fire detector according to the K degrees of difference. For example, take the average value of the K degrees of difference as the reliability of the target fire detector, or assign weights to each second target detection function according to factors such as the importance or accuracy of each second target detection function, so as to perform a weighted average on the K degrees of difference to obtain the reliability and improve the calculation accuracy of the reliability.

[0097] As described above, by comprehensively evaluating the reliability using the first target detection function and the second target detection function, it is equivalent to conducting a comparative analysis of the detection results of the target fire detector from multiple dimensions of the whole and the part, avoiding misjudgments that may be caused by single data or a single perspective, and thus more accurately determining whether the target fire detector is working reliably, improving the accuracy of subsequent status detection of the fire detector.

[0098] S5. Obtain several anomaly detection values corresponding to the target fire detector according to the reliability, the second reference detection value curve corresponding to the environmental state, the N initial detection values, and the first target detection function.

[0099] Among them, when the environmental state is in the normal state, the second reference detection value curve is consistent with the first reference detection value curve. When the environmental state is in the fire state, the second reference detection value curve is a curve drawn based on the historical detection data corresponding to the environmental state where the target fire detector is located being in the fire state. These historical detection data record the changes in the fire detection values at different times at this location. For example, the fluctuation ranges of parameters such as temperature, humidity, and smoke concentration at different time periods within a day. By statistically analyzing and fitting a large amount of historical data, the second reference detection value curve can be obtained as the basis for screening anomaly detection values in the target fire detector.

[0100] Optionally, according to the reliability level, the second reference detection value curve corresponding to the environmental state, the N initial detection values, and the first target detection function, a number of abnormal detection values corresponding to the target fire detector are obtained, including:

[0101] S51. If the environmental state is normal, then according to the reliability level and the second reference detection value curve, a first fluctuation detection value curve and a second fluctuation detection value curve are obtained. Among them, the detection value corresponding to each preset time point in the first fluctuation detection value curve is greater than the detection value corresponding to it in the second reference detection value curve, and the detection value corresponding to each preset time point in the second fluctuation detection value curve is less than the detection value corresponding to it in the second reference detection value curve.

[0102] S52. For any initial detection value, if the current initial detection value is not within the range corresponding to the first fluctuation detection value curve and the second fluctuation detection value curve, then the current initial detection value is determined as an abnormal detection value.

[0103] S53. Traverse the N initial detection values to obtain all the abnormal detection values.

[0104] Among them, the second reference detection value curve represents the ideal situation of the detection value in the normal state. The first fluctuation detection value curve and the second fluctuation detection value curve are based on the second reference detection value curve, and a normal fluctuation range boundary is determined according to the reliability level, serving as the threshold basis for screening abnormal detection values from the initial detection values.

[0105] In the normal state, the initial detection value should be within the reasonable fluctuation range determined according to the reliability level and the second reference detection value curve. If the initial detection value is greater than the value of the first fluctuation detection value curve at the corresponding preset time point, or less than the value of the second fluctuation detection value curve at the corresponding preset time point, that is, not within the range defined by these two curves, it means that the target fire detector is likely to have a malfunction or be affected by abnormal situations such as sudden interference in the environment. Then, the initial detection value is determined as an abnormal detection value.

[0106] As described above, by combining the reliability level and the second reference detection value curve to determine the first fluctuation detection value curve and the second fluctuation detection value curve, it can better adapt to the natural fluctuation of the detection value in the normal environmental state, thereby more accurately identifying abnormal detection values and improving the accuracy of subsequent status detection of the fire detector.

[0107] Optionally, according to the reliability level, the second reference detection value curve corresponding to the environmental state, the N initial detection values, and the first target detection function, a number of abnormal detection values corresponding to the target fire detector are obtained, and it also includes:

[0108] S54. If the environmental state is a fire state, obtain the reference gradient set corresponding to the second reference detection value curve and the third gradient set corresponding to the first target detection function, where the reference gradient set includes reference gradient values corresponding to N preset time points, and the third gradient set includes third gradient values corresponding to N preset time points.

[0109] S55. According to the reliability level and the reference gradient set, obtain the first fluctuation gradient set and the second fluctuation gradient set, where the first fluctuation gradient set includes first fluctuation gradient values corresponding to N preset time points, and the second fluctuation gradient set includes second fluctuation gradient values corresponding to N preset time points. The first fluctuation gradient value corresponding to each preset time point is greater than the corresponding reference gradient value, and the second fluctuation gradient value corresponding to each preset time point is less than the corresponding reference gradient value.

[0110] S56. For the third gradient value corresponding to any preset time point, if the third gradient value corresponding to the current preset time point is not within the range of the first fluctuation gradient value and the second fluctuation gradient value corresponding to the preset time point, determine the initial detection value corresponding to the current preset time point as an abnormal detection value.

[0111] S57. Traverse the N preset time points to obtain all the abnormal detection values.

[0112] Among them, the reference gradient set corresponding to the second reference detection value curve represents the ideal change trend of the detection value in the fire state. The first fluctuation gradient set and the second fluctuation gradient set are based on the reference gradient set, and according to the reliability level, a normal fluctuation range boundary is determined as the threshold basis for screening abnormal detection values from the initial detection values.

[0113] In the fire state, the third gradient value corresponding to the preset time point should be within the reasonable fluctuation range determined according to the reliability level and the reference gradient set. If the third gradient value corresponding to the preset time point is greater than the corresponding first fluctuation gradient value or less than the corresponding second fluctuation gradient value, that is, not within the defined gradient value range, it means that the target fire detector is likely to have a malfunction or be affected by abnormal situations such as sudden interference in the environment. Then, determine the initial detection value corresponding to the preset time point as an abnormal detection value.

[0114] As described above, by combining the reliability level and the reference gradient set corresponding to the second reference detection value curve to determine the first fluctuation gradient set and the second fluctuation gradient set, it can better adapt to the natural change trend of the detection value in the fire environment state, thereby more accurately identifying the abnormal detection values and improving the accuracy of subsequent status detection of the fire detector.

[0115] S6. According to all the abnormal detection values, obtain the detection status corresponding to the target fire detector.

[0116] Among them, multiple aspects such as the quantity, distribution, and occurrence frequency of all abnormal detection values are analyzed. For example, if the quantity of abnormal detection values is small and the distribution is relatively scattered, it may indicate that the detector is occasionally interfered with, but the overall working state is still relatively stable. If the quantity of abnormal detection values is large and they appear concentrated within a certain time period, it is very likely that the detector has a relatively serious fault.

[0117] The detection status can also be further judged by combining the degree to which the abnormal detection value deviates from the normal range. If the abnormal detection value only slightly deviates from the normal range, it may indicate that the detector is in a slightly abnormal state and further observation is required. If the abnormal detection value seriously deviates from the normal range, it may indicate that the detector can no longer work properly and immediate repair or replacement is needed.

[0118] Therefore, by analyzing multiple aspects such as the quantity, distribution, and occurrence frequency of all abnormal detection values, the detection status corresponding to the target fire detector is finally determined. Among them, the detection status can include different status categories such as normal, slightly abnormal, seriously abnormal, and faulty, so as to perform preventive maintenance or replacement on the fire detector, avoid problems from developing to the extent that seriously affects the normal operation of the fire detector, and thus improve the reliability and stability of the fire monitoring system.

[0119] In the embodiment of the present invention, the preset fitting method is selected according to the environmental state to fit the N initial detection values and the K initial detection value sets respectively, obtaining the first target detection function to analyze the overall characteristics of the detection data, and obtaining the second target detection function to analyze the local characteristics of the detection data, which can better adapt to the data characteristics in different dimensions, and the targeted fitting method can more accurately describe the data change trend, improving the characterization accuracy of the working state of the target fire detector; using the first target detection function and multiple second target detection functions to evaluate the reliability of the target fire detector, considering comprehensively from multiple perspectives of the whole and the local, and avoiding the limitations of single function evaluation through mutual verification of multiple functions, improving the evaluation accuracy of the reliability; comprehensively considering multiple factors such as the reliability, the second reference detection value curve corresponding to the environmental state, the initial detection value, and the first target detection function to determine the abnormal detection value, restricting and judging the initial detection value from different factors and aspects, improving the screening accuracy of the abnormal detection value, and being able to more comprehensively identify the true abnormal situations; finally, determining the detection status of the target fire detector according to all abnormal detection values, improving the accuracy of the status detection result of the target fire detector, and providing clear guidance for the operation and maintenance of the target fire detector.

[0120] Corresponding to the method for detecting the status of the fire detector in the above embodiment Figure 3The structural block diagram of the state detection device for the fire detector provided in the second embodiment of the present invention is given. For ease of description, only the parts related to the embodiments of the present invention are shown.

[0121] See Figure 3 , the state detection device for the fire detector includes:

[0122] A data acquisition module 31, configured to obtain N initial detection values corresponding to a target fire detector at N preset time points, and divide the N initial detection values into K initial detection value sets, where N and K are both integers greater than 1.

[0123] An environmental state judgment module 32, configured to obtain the environmental state corresponding to the location of the target fire detector according to the first reference detection value curve corresponding to the location of the target fire detector and the N initial detection values, where the environmental state is a normal state or a fire state.

[0124] A detection function fitting module 33, configured to respectively fit the N initial detection values and the K initial detection value sets according to a preset fitting method corresponding to the environmental state, to obtain a first target detection function corresponding to the N initial detection values of the target fire detector, and a second target detection function corresponding to each initial detection value set.

[0125] A reliability analysis module 34, configured to obtain the reliability corresponding to the target fire detector according to the first target detection function and the K second target detection functions.

[0126] An abnormal detection value screening module 35, configured to obtain a plurality of abnormal detection values corresponding to the target fire detector according to the reliability, the second reference detection value curve corresponding to the environmental state, the N initial detection values, and the first target detection function.

[0127] A detection state acquisition module 36, configured to obtain the detection state corresponding to the target fire detector according to all the abnormal detection values.

[0128] Optionally, the detection function fitting module 33 includes:

[0129] A first function fitting sub-module, configured to fit the N initial detection values with an m-th order polynomial to obtain a first reference detection function corresponding to the target fire detector and a first gradient set corresponding to the first reference detection function, where m is an integer greater than 1, and the first gradient set includes first gradient values corresponding to N preset time points.

[0130] The first function determination sub-module is used to update m = m - 1, and return to execute the first function fitting sub-module until the first gradient set meets the first preset condition corresponding to the environmental state or the updated m meets the second preset condition. Determine the first reference detection function corresponding to the condition as the first target detection function of the target fire detector, and determine the number of times corresponding to the first target detection function as the reference number c, where c is an integer greater than 0.

[0131] The second function fitting sub-module is used to fit any initial detection value set with a polynomial of degree c to obtain the second reference detection function corresponding to the target fire detector for the current initial detection value set and the second gradient set corresponding to the second reference detection function, where the number of gradient values in the second gradient set corresponding to the current initial detection value set is the same as the number of initial detection values in the current initial detection value set.

[0132] The second function determination sub-module is used to update c = c - 1, and return to execute the second function fitting sub-module until the second gradient set meets the first preset condition corresponding to the environmental state or the updated c meets the second preset condition. Determine the second reference detection function corresponding to the condition as the second target detection function of the target fire detector for the current initial detection value set.

[0133] The set traversal sub-module is used to traverse all initial detection value sets to obtain the second target detection function of the target fire detector for each initial detection value set.

[0134] Optionally, in the first function determination sub-module, the first preset condition includes:

[0135] If the environmental state is a normal state, the first gradient set meeting the first preset condition corresponding to the environmental state means that there is a first gradient value in the first gradient set that is less than the first preset gradient value or greater than the second preset gradient value;

[0136] If the environmental state is a fire state, the first gradient set meeting the first preset condition corresponding to the environmental state means that there is a first gradient value in the first gradient set that is less than the third preset gradient value;

[0137] The second preset condition includes:

[0138] The updated m is less than the preset polynomial degree.

[0139] Optionally, the reliability analysis module 34 includes:

[0140] A time point range obtaining sub-module, which is used for any second target detection function to obtain the time point range corresponding to the current second target detection function according to the preset time points corresponding to the initial detection value set corresponding to the current second target detection function.

[0141] A difference degree calculating sub-module, which is used to calculate the difference degree between the current second target detection function and the first target detection function within the time point range.

[0142] A function traversing sub-module, which is used to traverse K second target detection functions and obtain the difference degree between each second target detection function and the first target detection function.

[0143] A reliability calculating sub-module, which is used to calculate the reliability corresponding to the target fire detector according to the K difference degrees.

[0144] Optionally, the abnormal detection value screening module 35 includes:

[0145] A fluctuation curve obtaining sub-module, which is used to, if the environmental state is a normal state, obtain a first fluctuation detection value curve and a second fluctuation detection value curve according to the reliability and the second reference detection value curve, where the detection value corresponding to each preset time point in the first fluctuation detection value curve is greater than the detection value corresponding to the second reference detection value curve, and the detection value corresponding to each preset time point in the second fluctuation detection value curve is less than the detection value corresponding to the second reference detection value curve.

[0146] A first abnormal value screening sub-module, which is used for any initial detection value. If the current initial detection value is not within the range corresponding to the first fluctuation detection value curve and the second fluctuation detection value curve, then the current initial detection value is determined as an abnormal detection value.

[0147] An initial detection value traversing sub-module, which is used to traverse N initial detection values and obtain all the abnormal detection values.

[0148] Optionally, the abnormal detection value screening module 35 includes:

[0149] A gradient set obtaining sub-module, which is used to, if the environmental state is a fire state, obtain a reference gradient set corresponding to the second reference detection value curve and a third gradient set corresponding to the first target detection function, where the reference gradient set includes reference gradient values corresponding to N preset time points, and the third gradient set includes third gradient values corresponding to N preset time points.

[0150] A fluctuation gradient value acquisition sub-module, configured to obtain a first fluctuation gradient set and a second fluctuation gradient set according to the reliability level and the reference gradient set, where the first fluctuation gradient set includes first fluctuation gradient values corresponding to N preset time points, and the second fluctuation gradient set includes second fluctuation gradient values corresponding to N preset time points. The first fluctuation gradient value corresponding to each preset time point is greater than the corresponding reference gradient value, and the second fluctuation gradient value corresponding to each preset time point is less than the corresponding reference gradient value.

[0151] A second outlier screening sub-module, configured to, for a third gradient value corresponding to any preset time point, if the third gradient value corresponding to the current preset time point is not within the range of the first fluctuation gradient value and the second fluctuation gradient value corresponding to the preset time point, determine the initial detection value corresponding to the current preset time point as an outlier detection value.

[0152] A preset time point traversal sub-module, configured to traverse the N preset time points to obtain all the outlier detection values.

[0153] Optionally, the data acquisition module 31 includes the following steps:

[0154] A data acquisition sub-module, configured to obtain the identification information of the main control module, the drive module, the detection module, and the target fire detector, where the drive module and the target fire detector are respectively connected to the loop bus.

[0155] A test information output sub-module, configured to, through the main control module, control the drive module to output test information to the loop bus during a first preset period, where the test information includes the identification information of the target fire detector.

[0156] A response information acquisition sub-module, configured to, through the detection module, obtain the response information of the target fire detector from the loop bus during a second preset period, where the response information includes N initial detection values corresponding to the target fire detector at N preset time points.

[0157] It should be noted that, for the information interaction, execution process, etc. between the above modules, since they are based on the same concept as the method embodiment of the present invention, for their specific functions and the technical effects brought, reference can be specifically made to the method embodiment part, and details are not described herein again.

[0158] Figure 4 This is a schematic structural diagram of a computer device provided in Embodiment 3 of the present invention. As Figure 4 shown, the computer device of this embodiment includes: at least one processor ( Figure 4 only one is shown in the figure), a memory, and a computer program stored in the memory and executable on at least one processor. When the processor executes the computer program, the steps in any of the above method embodiments for detecting the state of a fire detector are implemented.

[0159] The computer device may include, but is not limited to, a processor and a memory. Those skilled in the art can understand that Figure 4 This is only an example of a computer device and does not constitute a limitation on the computer device. The computer device may include more or fewer components than shown in the figure, or combine certain components, or different components. For example, it may also include a network interface, a display screen, and an input device, etc.

[0160] The so-called processor may be a CPU, and the processor may also be other general-purpose processors, digital signal processors (DSPs), application specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0161] The memory includes a readable storage medium, an internal memory, etc. Among them, the internal memory may be the memory of the computer device, and the internal memory provides an environment for the operation of the operating system and computer-readable instructions in the readable storage medium. The readable storage medium may be the hard disk of the computer device, and in some other embodiments, it may also be an external storage device of the computer device. For example, a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device. Further, the memory may also include both the internal storage unit and the external storage device of the computer device. The memory is used to store the operating system, application programs, a boot loader, data, and other programs, such as the program code of a computer program. The memory may also be used to temporarily store the data that has been output or will be output.

[0162] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above division of each functional unit and module is used as an example. In actual applications, the above functions can be allocated to different functional units and modules according to needs, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiments can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. In addition, the specific names of each functional unit and module are only for the convenience of mutual distinction and do not limit the protection scope of the present invention. The specific working process of the units and modules in the above device can refer to the corresponding process in the foregoing method embodiments and will not be elaborated herein. If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, to implement all or part of the processes in the above method embodiments of the present invention, a computer program can be used to instruct the relevant hardware to complete. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, the steps of the above method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in the form of source code, object code, executable file or some intermediate form, etc. The computer-readable medium can at least include: any entity or device capable of carrying the computer program code, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disc, etc. In some jurisdictions, according to legislation and patent practice, the computer-readable medium cannot be an electrical carrier signal and a telecommunication signal.

[0163] All or part of the processes in the above method embodiments of the present invention can also be completed by a computer program product. When the computer program product runs on a computer device, it enables the computer device to execute and implement the steps in the above method embodiments.

[0164] In the above embodiments, the descriptions of the respective embodiments have their own emphases. For the parts not detailed or recorded in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0165] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in connection with the embodiments disclosed herein can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are executed in hardware or software depends on the specific application and design constraints of the technical solution. A professional technician may use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present invention.

[0166] In the embodiments provided by the present invention, it should be understood that the disclosed apparatus / computer device and method can be implemented in other ways. For example, the apparatus / computer device embodiments described above are merely illustrative. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the apparatus or unit can be in an electrical, mechanical or other form.

[0167] The units described as separate components may or may not be physically separated. The components displayed as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0168] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements for some of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be included in the protection scope of the present invention.

Claims

1. A method for detecting the state of a fire detector, characterized in that: The state detection method of the fire detector comprises: Obtaining N initial detection values ​​corresponding to the target fire detector at N preset time points, and dividing the N initial detection values ​​into K initial detection value sets, where N and K are both integers greater than 1; According to the first reference detection value curve corresponding to the location of the target fire detector and the N initial detection values, an environmental state corresponding to the location of the target fire detector is obtained, wherein the environmental state is a normal state or a fire state; Fitting the N initial detection values ​​and the K initial detection value sets respectively according to a preset fitting method corresponding to the environmental state to obtain a first target detection function corresponding to the N initial detection values ​​of the target fire detector and a second target detection function corresponding to each initial detection value set; Obtaining a reliability level corresponding to the target fire detector according to the first target detection function and the K second target detection functions; Obtaining a number of abnormal detection values ​​corresponding to the target fire detector according to the reliability, the second reference detection value curve corresponding to the environmental state, the N initial detection values ​​and the first target detection function; According to all abnormal detection values, the detection status corresponding to the target fire detector is obtained.

2. The method for detecting the state of a fire detector according to claim 1, characterized in that: The N initial detection values ​​and the K initial detection value sets are fitted respectively according to the preset fitting method corresponding to the environmental state to obtain a first target detection function corresponding to the N initial detection values ​​of the target fire detector and a second target detection function corresponding to each initial detection value set, including: Fitting the N initial detection values ​​with an m-order polynomial to obtain a first reference detection function corresponding to the target fire detector and a first gradient set corresponding to the first reference detection function, wherein m is an integer greater than 1, and the first gradient set includes first gradient values ​​corresponding to N preset time points; Update m=m-1, return to the step of fitting the N initial detection values ​​with an m-order polynomial to obtain a first reference detection function corresponding to the target fire detector and a first gradient set corresponding to the first reference detection function, until the first gradient set satisfies the first preset condition corresponding to the environmental state or the updated m satisfies the second preset condition, determine the first reference detection function corresponding to the condition as the first target detection function corresponding to the target fire detector, and determine the number corresponding to the first target detection function as the reference number c, where c is an integer greater than 0; For any initial detection value set, a c-order polynomial is used to fit the current initial detection value set to obtain a second reference detection function corresponding to the current initial detection value set and a second gradient set corresponding to the second reference detection function of the target fire detector, wherein the number of gradient values ​​in the second gradient set corresponding to the current initial detection value set is consistent with the number of initial detection values ​​in the current initial detection value set; Update c=c-1, return to the step of fitting the current initial detection value set with the c-order polynomial to obtain the second reference detection function corresponding to the target fire detector for the current initial detection value set and the second gradient set corresponding to the second reference detection function, until the second gradient set satisfies the first preset condition corresponding to the environmental state or the updated c satisfies the second preset condition, and the second reference detection function corresponding to the condition being met is determined as the second target detection function corresponding to the target fire detector for the current initial detection value set; All initial detection value sets are traversed to obtain a second target detection function corresponding to each initial detection value set of the target fire detector.

3. The method for detecting the state of a fire detector according to claim 2, characterized in that: The first preset condition includes: If the environmental state is a normal state, the first gradient set satisfies the first preset condition corresponding to the environmental state means that there is a first gradient value in the first gradient set that is less than a first preset gradient value or greater than a second preset gradient value; If the environmental state is a fire state, the first gradient set satisfies the first preset condition corresponding to the environmental state, which means that there is a first gradient value in the first gradient set that is less than a third preset gradient value; The second preset condition includes: The updated m is smaller than the preset polynomial degree.

4. The method for detecting the state of a fire detector according to claim 1, characterized in that: The step of obtaining the reliability corresponding to the target fire detector according to the first target detection function and the K second target detection functions includes: For any second target detection function, according to the preset time points corresponding to the initial detection value set corresponding to the current second target detection function, a time point range corresponding to the current second target detection function is obtained; Calculate the difference between the current second target detection function and the first target detection function within the time point range; Traversing K second target detection functions, and obtaining the degree of difference between each second target detection function and the first target detection function; The reliability level corresponding to the target fire detector is calculated based on the K difference levels.

5. The method for detecting the state of a fire detector according to claim 1, characterized in that: The step of obtaining a plurality of abnormal detection values ​​corresponding to the target fire detector according to the reliability, the second reference detection value curve corresponding to the environmental state, the N initial detection values ​​and the first target detection function comprises: If the environmental state is a normal state, a first fluctuation detection value curve and a second fluctuation detection value curve are obtained according to the reliability and the second reference detection value curve, wherein the detection value corresponding to each preset time point in the first fluctuation detection value curve is greater than the detection value corresponding to the second reference detection value curve, and the detection value corresponding to each preset time point in the second fluctuation detection value curve is less than the detection value corresponding to the second reference detection value curve; For any initial detection value, if the current initial detection value is not within the range corresponding to the first fluctuation detection value curve and the second fluctuation detection value curve, the current initial detection value is determined as an abnormal detection value; Traverse N initial detection values ​​to obtain all abnormal detection values.

6. The method for detecting the state of a fire detector according to claim 1, characterized in that: The method of obtaining a plurality of abnormal detection values ​​corresponding to the target fire detector according to the reliability, the second reference detection value curve corresponding to the environmental state, the N initial detection values ​​and the first target detection function further includes: If the environmental state is a fire state, a reference gradient set corresponding to the second reference detection value curve and a third gradient set corresponding to the first target detection function are obtained, wherein the reference gradient set includes reference gradient values ​​corresponding to N preset time points, and the third gradient set includes third gradient values ​​corresponding to N preset time points; According to the reliability and the reference gradient set, a first fluctuation gradient set and a second fluctuation gradient set are obtained, wherein the first fluctuation gradient set includes first fluctuation gradient values ​​corresponding to N preset time points, and the second fluctuation gradient set includes second fluctuation gradient values ​​corresponding to N preset time points, and the first fluctuation gradient value corresponding to each preset time point is greater than the corresponding reference gradient value, and the second fluctuation gradient value corresponding to each preset time point is less than the corresponding reference gradient value; For the third gradient value corresponding to any preset time point, if the third gradient value corresponding to the current preset time point is not within the range of the first fluctuation gradient value and the second fluctuation gradient value corresponding to the preset time point, the initial detection value corresponding to the current preset time point is determined as the abnormal detection value; Traverse N preset time points to obtain all anomaly detection values.

7. The method for detecting the state of a fire detector according to claim 1, characterized in that: The obtaining of N initial detection values ​​corresponding to the target fire detector at N preset time points, and dividing the N initial detection values ​​into K initial detection value sets, includes: Obtaining identification information of a main control module, a driving module, a detection module and the target fire detector, wherein the driving module and the target fire detector are respectively connected to a loop bus; Controlling the driving module to output test information to the loop bus during a first preset period of time through the main control module, wherein the test information includes identification information of the target fire detector; The detection module obtains response information of the target fire detector from the loop bus in a second preset time period, wherein the response information includes N initial detection values ​​corresponding to the target fire detector at N preset time points.

8. A fire detector status detection device, characterized in that: The state detection device of the fire detector comprises: A data acquisition module, used to acquire N initial detection values ​​corresponding to the target fire detector at N preset time points, and divide the N initial detection values ​​into K initial detection value sets, wherein N and K are both integers greater than 1; An environmental state judgment module, used to obtain the environmental state corresponding to the location of the target fire detector according to the first reference detection value curve corresponding to the location of the target fire detector and the N initial detection values, wherein the environmental state is a normal state or a fire state; a detection function fitting module, used to fit the N initial detection values ​​and the K initial detection value sets respectively according to a preset fitting method corresponding to the environmental state, to obtain a first target detection function corresponding to the N initial detection values ​​of the target fire detector, and a second target detection function corresponding to each initial detection value set; A reliability analysis module, used for obtaining the reliability corresponding to the target fire detector according to the first target detection function and K second target detection functions; an abnormal detection value screening module, used to obtain a number of abnormal detection values ​​corresponding to the target fire detector according to the reliability, the second reference detection value curve corresponding to the environmental state, the N initial detection values ​​and the first target detection function; The detection status acquisition module is used to obtain the detection status corresponding to the target fire detector according to all abnormal detection values.

9. A computer device, characterized in that: The computer device includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the method for detecting the state of a fire detector according to any one of claims 1 to 7 is implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method for detecting the state of a fire detector according to any one of claims 1 to 7 is implemented.

Images