Performance evaluation method, device and equipment for gas leakage detection system

Abstract

The invention relates to the technical field of safety production monitoring, and discloses a method, a device and equipment for evaluating the performance of a gas leakage detection system. A gas leakage detection system is adopted to collect a plurality of first gas concentration signals and a plurality of second gas concentration signals in the target area; performing signal decomposition and reconstruction on the first gas concentration signal and the second gas concentration signal to obtain a first target concentration signal and a second target concentration signal; constructing a sample database based on the first target concentration signal and the second target concentration signal; and based on the sample database, determining the accuracy rate and the false alarm rate of the gas leakage detection system. According to the method, the gas leakage detection system is adopted to collect the gas concentration signals in the standard gas environment and the interference environment respectively, the performance in the ideal environment is considered, and the performance in the complex interference environment is particularly concerned, so that the evaluation result is more suitable for the actual application scene.

Description

Technical Field

[0001] The present invention relates to the technical field of production safety monitoring, and in particular to a performance evaluation method, device and equipment for a gas leak detection system. Background Art

[0002] Gas leaks not only have a serious impact on industrial production, but may also bring serious environmental and public safety risks. For example, gas leaks may cause fires, explosions, suffocation, etc. Therefore, timely and accurate detection and monitoring of gas leaks is crucial.

[0003] Existing gas leak detection systems mainly focus on performance evaluation under standard laboratory conditions. Although the basic functions and performance indicators of the gas leak detection system can be evaluated, it cannot fully simulate the various extreme environments that may be encountered in actual applications, resulting in incomplete performance evaluation. Summary of the invention

[0004] In view of this, the present invention provides a performance evaluation method, device and equipment for a gas leak detection system to solve the problem that the existing gas leak detection system focuses on performance evaluation under standard laboratory conditions, resulting in incomplete performance evaluation.

[0005] In a first aspect, the present invention provides a method for evaluating the performance of a gas leak detection system, the method comprising:

[0006] Under a standard gas environment, a gas leak detection system is used to collect a plurality of first gas concentration signals in a target area;

[0007] Under various interference environments, a gas leak detection system is used to collect multiple second gas concentration signals in the target area;

[0008] Decomposing and reconstructing the plurality of first gas concentration signals and the plurality of second gas concentration signals respectively to obtain a plurality of first target concentration signals and a plurality of second target concentration signals, wherein the background noise and interference signal of the target concentration signals are less than the corresponding gas concentration signals;

[0009] constructing a sample database based on the plurality of first target concentration signals and the plurality of second target concentration signals;

[0010] Based on the sample database, determine the accuracy and false alarm rate of the gas leak detection system during gas detection.

[0011] The performance evaluation method of the gas leak detection system provided in the embodiment of the present invention collects multiple first gas concentration signals and multiple second gas concentration signals in the target area by using the gas leak detection system in a standard gas environment and an interference environment respectively. It not only takes into account the standard laboratory environment, but also introduces multiple interference environments, and can simulate various complex situations that may be encountered in actual applications, so that the evaluation result is closer to the real scene, thereby improving the practicality and credibility of the evaluation. By decomposing and reconstructing the above-collected gas concentration signal, the background noise and interference signal in the signal can be effectively removed, so that the target concentration signal is purer, and the accuracy of subsequent data analysis is improved. Through the target concentration signals under different environments, a comprehensive and diverse sample database is constructed, which can better reflect the performance of the system under various environmental conditions, so that the accuracy rate and false alarm rate are calculated based on the sample database, so that the performance evaluation of the system is more scientific and rigorous, and the reliability and trustworthiness of the system are enhanced. Not only the performance under an ideal environment is considered, but also the performance under a complex interference environment is paid special attention to, so that the evaluation result is more in line with the actual application scenario.

[0012] In an optional implementation, the plurality of first gas concentration signals and the plurality of second gas concentration signals are respectively subjected to signal decomposition and reconstruction to obtain a plurality of first target concentration signals and a plurality of second target concentration signals, including:

[0013] For any gas concentration signal, the gas concentration signal is decomposed into a residual component and a plurality of intrinsic mode functions;

[0014] Calculate the correlation coefficient between the gas concentration signal and each intrinsic mode function;

[0015] Filter out the intrinsic mode functions whose correlation coefficients are greater than a preset threshold;

[0016] The unfiltered intrinsic mode functions and residual components are reconstructed to obtain the target concentration signal corresponding to the gas concentration signal.

[0017] The performance evaluation method of the gas leak detection system provided in an embodiment of the present invention decomposes the gas concentration signal and filters out the intrinsic mode functions whose correlation coefficients are greater than a preset threshold, thereby effectively eliminating the high-noise and high-interference parts, so that the reconstructed target concentration signal has less noise and interference, which helps to improve the evaluation accuracy.

[0018] In an optional implementation, for any gas concentration signal, the gas concentration signal is decomposed into a residual component and a plurality of intrinsic mode functions, including:

[0019] Determine the local maximum and minimum points of the gas concentration signal;

[0020] Based on the local maximum and minimum points, the upper and lower envelopes are fitted using cubic spline interpolation method.

[0021] Calculate the average of the upper envelope and the lower envelope to obtain the mean envelope;

[0022] Determine the difference between the gas concentration signal and the mean envelope. If the difference does not meet the decomposition requirements, use the difference as the gas concentration signal for the next decomposition, and return to the step of determining the local maximum point and the local minimum point of the gas concentration signal until the difference meets the decomposition requirements, and use the difference as the intrinsic mode function of this decomposition;

[0023] The difference between the gas concentration signal and all intrinsic mode functions is taken as the residual component of this decomposition;

[0024] The residual component of this decomposition is used as the gas concentration signal for the next decomposition, and the process returns to the step of determining the local maximum and local minimum points of the gas concentration signal, until the sum of the number of local maximum and local minimum points of the residual component of this decomposition is less than the preset number threshold, and the final residual component is obtained.

[0025] The performance evaluation method of the gas leak detection system provided in the embodiment of the present invention decomposes the complex gas concentration signal into multiple intrinsic mode functions and a residual component through signal decomposition, so that each component can be presented more clearly to facilitate further analysis. Noise and other interference components are gradually removed during the iteration process, so that the final intrinsic mode function and residual component can better reflect the actual gas concentration changes, thereby improving the quality and reliability of the signal.

[0026] In an optional embodiment, constructing a sample database based on a plurality of first target concentration signals and a plurality of second target concentration signals includes:

[0027] Based on the multiple first target concentration signals, construct multiple positive samples;

[0028] constructing multiple negative samples based on multiple second target concentration signals;

[0029] Based on multiple positive samples and multiple negative samples, a sample database is constructed.

[0030] The performance evaluation method of the gas leak detection system provided in the embodiment of the present invention can accurately reflect the detection results of the gas leak detection system under standard environmental conditions through positive samples, providing a reliable basis for subsequent evaluation. The negative samples can simulate various complex situations that may be encountered in actual applications, so that the evaluation results are closer to the real scene. By combining positive samples and negative samples, a comprehensive and diverse sample database is constructed, covering the detection results under different conditions, thereby improving the comprehensiveness and scientificity of the evaluation.

[0031] In an optional embodiment, multiple positive samples are constructed based on multiple first target concentration signals, including:

[0032] For any first target concentration signal, when there is gas in the standard gas environment and the first target concentration signal indicates the presence of gas, the first target concentration signal is taken as a positive sample;

[0033] When there is no gas in the standard gas environment and the first target concentration signal indicates that there is no gas, the first target concentration signal is used as a positive and negative sample;

[0034] The positive samples and the positive negative samples corresponding to the plurality of first target concentration signals are taken as positive samples.

[0035] The performance evaluation method of the gas leak detection system provided in the embodiment of the present invention verifies whether the gas leak detection system can accurately detect the presence of gas when gas is present through positive and negative samples, thereby ensuring the sensitivity and accuracy of the system, simulating the situation in which gas exists in a real environment, and verifies whether the gas leak detection system can correctly judge when no gas is present through positive and negative samples. The combination of positive and negative samples helps to comprehensively evaluate the performance of the gas leak detection system in a standard gas environment.

[0036] In an optional embodiment, based on a plurality of second target concentration signals, a plurality of negative samples are constructed, including:

[0037] For any second target concentration signal, when there is no gas in the interference environment corresponding to the second target concentration signal and the second target concentration signal indicates the presence of gas, the second target concentration signal is taken as a negative positive sample;

[0038] When there is gas in the interference environment corresponding to the second target concentration signal and the second target concentration signal indicates that there is no gas, the second target concentration signal is used as a negative sample;

[0039] The negative positive samples and negative negative samples corresponding to the multiple second target concentration signals are used as negative samples.

[0040] The performance evaluation method of the gas leak detection system provided in the embodiment of the present invention uses negative-positive samples to identify that when there is no actual gas leakage, the system mistakenly detects the presence of gas, that is, a false alarm situation, simulates the false alarm situation that may occur in the system under various interference environments, and makes the evaluation results closer to the complex scenarios in actual applications. It uses negative-negative samples to identify that when there is an actual gas leakage, the system fails to correctly detect the presence of gas, that is, a missed alarm situation. The combination of negative-positive samples and negative-negative samples helps to comprehensively evaluate the performance of the gas leak detection system in complex interference environments.

[0041] In an optional implementation, based on the sample database, determining the accuracy and false alarm rate of the gas leak detection system during gas detection includes:

[0042] For any negative sample in the sample database, if the second target concentration signal corresponding to the negative sample meets the corresponding preset elimination rule, the negative sample is eliminated from the sample database;

[0043] The ratio of the number of positive samples in the sample database to the number of all samples in the sample database is used as the accuracy of the gas leak detection system in gas detection;

[0044] The ratio of the number of positive and negative samples in the sample database to the number of all positive samples in the sample database is used as the false alarm rate of the gas leak detection system during gas detection.

[0045] The performance evaluation method of the gas leak detection system provided in the embodiment of the present invention can ensure that the data in the sample database is valid and meets the evaluation criteria by eliminating negative samples that do not meet the preset elimination rules. At the same time, it can reduce false alarms and missed alarms caused by environmental or measurement errors, making the evaluation more accurate. The accuracy rate reflects the proportion of correct detections by the system in the overall samples, and the false alarm rate evaluates the probability of the system mistakenly detecting the presence of gas when there is no gas.

[0046] In a second aspect, the present invention provides a performance evaluation device for a gas leak detection system, the device comprising:

[0047] A first acquisition module is used to acquire a plurality of first gas concentration signals in a target area using a gas leak detection system under a standard gas environment;

[0048] The second acquisition module is used to respectively acquire a plurality of second gas concentration signals in a target area using a gas leak detection system under various interference environments;

[0049] A signal processing module, used for performing signal decomposition and reconstruction on the plurality of first gas concentration signals and the plurality of second gas concentration signals respectively, to obtain a plurality of first target concentration signals and a plurality of second target concentration signals, wherein the background noise and interference signal of the target concentration signals are less than the corresponding gas concentration signals;

[0050] A construction module, used to construct a sample database based on a plurality of first target concentration signals and a plurality of second target concentration signals;

[0051] The evaluation module is used to determine the accuracy and false alarm rate of the gas leak detection system during gas detection based on a sample database.

[0052] In a third aspect, the present invention provides a computer device, comprising: a memory and a processor, the memory and the processor being communicatively connected to each other, the memory storing computer instructions, and the processor executing the performance evaluation method of the gas leak detection system of the first aspect or any corresponding embodiment thereof by executing the computer instructions.

[0053] In a fourth aspect, the present invention provides a computer-readable storage medium having computer instructions stored thereon, the computer instructions being used to enable a computer to execute the performance evaluation method for a gas leak detection system of the first aspect or any corresponding embodiment thereof. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0055] Figure 1 is a flow chart of a method for evaluating the performance of a gas leak detection system according to an embodiment of the present invention;

[0056] Figure 2 is a structural block diagram of a performance evaluation device for a gas leak detection system according to an embodiment of the present invention;

[0057] Figure 3 It is a schematic diagram of the hardware structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0059] Existing gas leak detection systems mainly focus on performance evaluation under standard laboratory conditions, which is not comprehensive. The performance evaluation method of the gas leak detection system provided by the embodiment of the present invention not only considers the performance under ideal conditions, but also pays special attention to the performance under complex interference environments, so that the evaluation results are more in line with actual application scenarios.

[0060] According to an embodiment of the present invention, an embodiment of a performance evaluation method for a gas leak detection system is provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0061] In this embodiment, a performance evaluation method of a gas leak detection system is provided, which can be used in a terminal. Figure 1 is a flow chart of a method for evaluating the performance of a gas leak detection system according to an embodiment of the present invention. Figure 1 As shown, the process includes the following steps:

[0062] Step S101, in a standard gas environment, a gas leak detection system is used to collect multiple first gas concentration signals in a target area. Specifically, the standard gas environment is the standard laboratory environment used in the evaluation of existing gas leak detection systems. The target area refers to an area within a certain range from the gas leak detection system. For example, gas containers with different methane concentrations can be placed in sequence at 5m, 10m, 15m, 20m, 25m, 30m, 40m, and 50m from the installation location of the gas leak detection system. A gas leak detection system, such as a laser pan-tilt detection device, is used to collect the gas concentration of the gas container at each position, and obtain multiple first gas concentration signals.

[0063] Step S102, in a variety of interference environments, a gas leak detection system is used to collect multiple second gas concentration signals in the target area. Specifically, the interference environment can be shaking, darkness, reflection, rain and fog. For any interference environment, the gas leak detection system is used to collect at the gas containers at the multiple locations listed in step S101 to obtain multiple second gas concentration signals.

[0064] Step S103, respectively decompose and reconstruct the multiple first gas concentration signals and the multiple second gas concentration signals to obtain multiple first target concentration signals and multiple second target concentration signals, wherein the background noise and interference signal of the target concentration signal are less than the corresponding gas concentration signal. Specifically, due to the existence of the etalon effect, the background fluctuation interference will be caused to the gas concentration signal collected by the gas leak detection system. Therefore, the gas concentration signal can be decomposed and reconstructed by EMD (Empirical Mode Decomposition), which can improve the purity of the signal, be closer to the actual gas concentration, and help improve the accuracy of the evaluation.

[0065] Step S104, constructing a sample database based on the multiple first target concentration signals and the multiple second target concentration signals. Specifically, the optimized first target concentration signals and the second target concentration signals are integrated into a sample database, which contains data under multiple environments, making the sample database richer and more diverse, and can better reflect the actual performance of the system, which is helpful for comprehensively evaluating the system performance.

[0066] Step S105, based on the sample database, determine the accuracy and false alarm rate of the gas leak detection system during gas detection. Specifically, when evaluating the system performance of the gas leak detection system, the accuracy and false alarm rate are usually calculated. The accuracy reflects the proportion of correct detections by the system in the overall sample, and the false alarm rate is used to evaluate the probability that the system mistakenly detects the presence of gas when there is no gas. By calculating the accuracy and false alarm rate, the performance of the system during gas detection can be effectively evaluated.

[0067] The performance evaluation method of the gas leak detection system provided in the embodiment of the present invention collects multiple first gas concentration signals and multiple second gas concentration signals in the target area by using the gas leak detection system in a standard gas environment and an interference environment respectively. It not only takes into account the standard laboratory environment, but also introduces multiple interference environments, and can simulate various complex situations that may be encountered in actual applications, so that the evaluation result is closer to the real scene, thereby improving the practicality and credibility of the evaluation. By decomposing and reconstructing the above-collected gas concentration signal, the background noise and interference signal in the signal can be effectively removed, so that the target concentration signal is purer, and the accuracy of subsequent data analysis is improved. Through the target concentration signals under different environments, a comprehensive and diverse sample database is constructed, which can better reflect the performance of the system under various environmental conditions, so that the accuracy rate and false alarm rate are calculated based on the sample database, so that the performance evaluation of the system is more scientific and rigorous, and the reliability and trustworthiness of the system are enhanced. Not only the performance under an ideal environment is considered, but also the performance under a complex interference environment is paid special attention to, so that the evaluation result is more in line with the actual application scenario.

[0068] In this embodiment, a performance evaluation method of a gas leak detection system is provided, which can be used in the above-mentioned terminal. The method specifically includes the following steps:

[0069] Step S201: Under a standard gas environment, a gas leak detection system is used to collect multiple first gas concentration signals in a target area. Figure 1 Step S101 of the illustrated embodiment will not be described in detail here.

[0070] Step S202: Under various interference environments, a gas leak detection system is used to collect multiple second gas concentration signals in the target area. Figure 1Step S102 of the illustrated embodiment will not be described in detail here.

[0071] Step S203, performing signal decomposition and reconstruction on the multiple first gas concentration signals and the multiple second gas concentration signals respectively to obtain multiple first target concentration signals and multiple second target concentration signals, wherein the background noise and interference signal of the target concentration signal are less than those of the corresponding gas concentration signal.

[0072] Specifically, the above step S203 includes:

[0073] Step S2031: for any gas concentration signal, decompose the gas concentration signal into a residual component and a plurality of intrinsic mode functions.

[0074] In some optional implementations, the above step S2031 includes:

[0075] Step a1, determine the local maximum and minimum points of the gas concentration signal. Specifically, find all the local maximum and minimum points in the gas concentration signal, which are used to construct the envelope curve later, so as to better capture the oscillation characteristics of the signal.

[0076] Step a2, based on the local maximum points and local minimum points, the upper envelope and the lower envelope are fitted using the cubic spline interpolation method. Specifically, all local maximum points are connected using the cubic spline interpolation method to form an upper envelope, and all local minimum points are connected using the same method to form a lower envelope. The cubic spline interpolation method can generate a smooth and continuous envelope, accurately reflecting the upper and lower boundaries of the signal, avoiding the discontinuity and errors that may be introduced by simple linear interpolation.

[0077] Step a3, calculate the average value of the upper envelope and the lower envelope to obtain the mean envelope. Specifically, calculate the average value of the upper envelope and the lower envelope at each point to form an intermediate reference line, namely the mean envelope. The mean envelope provides the center position of the signal oscillation, which is helpful for subsequent difference calculation and ensures that the decomposition result is closer to the intrinsic mode function of the real signal.

[0078] Step a4, determine the difference between the gas concentration signal and the mean envelope. If the difference does not meet the decomposition requirements, use the difference as the gas concentration signal for the next decomposition, and return to the step of determining the local maximum point and the local minimum point of the gas concentration signal until the difference meets the decomposition requirements, and use the difference as the intrinsic mode function of this decomposition. Specifically, calculate the difference between the gas concentration signal and the mean envelope. If the difference does not meet the preset decomposition requirements, use the difference as a new gas concentration signal and start decomposition again from step a1. Repeat this process until the difference meets the decomposition requirements, and then use the difference as an intrinsic mode function. Among them, the decomposition requirement can be to judge that the difference meets the requirements at any given point, and its upper and lower waves contain an equal number of extreme points, and its average value is zero within the time range of the entire signal. The high-frequency components are gradually removed through the iterative process to ensure that the final intrinsic mode function has a single frequency characteristic. The iterative process makes the final intrinsic mode function purer and reduces the influence of noise and other interference.

[0079] Step a5: The difference between the gas concentration signal and all the intrinsic mode functions is used as the residual component of this decomposition. Specifically, all the extracted intrinsic mode functions are subtracted from the gas concentration signal to obtain the remaining part, i.e., the residual component. The residual component usually represents the low-frequency or trend part of the signal and retains the information of long-term changes.

[0080] Step a6, taking the residual component of this decomposition as the gas concentration signal for the next decomposition, and returning to the step of determining the local maximum and local minimum points of the gas concentration signal, until the sum of the number of local maximum and local minimum points of the residual component of this decomposition is less than the preset number threshold, and obtaining the final residual component. Specifically, the current residual component is regarded as a new gas concentration signal, and the process from step a1 to step a5 is repeated to continue decomposition. When the sum of the number of local maximum and local minimum points of the residual component is less than the set threshold, the decomposition is stopped, and the residual component at this time is regarded as the final low-frequency component or trend item. Through multiple iterations, it is ensured that all frequency components of the signal are fully extracted, from high frequency to low frequency, and finally a complete signal decomposition is achieved. Optionally, any gas concentration signal can be represented by the following formula (1), which includes multiple intrinsic mode functions and one residual component.

[0081]

[0082] Where x(t) represents the gas concentration signal; m represents the number of intrinsic mode functions; IMF k (t) represents the kth intrinsic mode function; r(t) represents the residual component.

[0083] Step S2032, calculate the correlation coefficient between the gas concentration signal and each intrinsic mode function. Specifically, the correlation coefficient is used to measure the linear correlation between the original gas concentration signal and each intrinsic mode function. The larger the correlation coefficient, the more relevant the intrinsic mode function is to some significant features in the gas concentration signal. The significant features may be noise or interference. Optionally, the correlation coefficient may be calculated by the following formula (2).

[0084] ρk=corr(x(t),IMFk(t))(2)

[0085] Wherein, ρk represents the correlation coefficient between the kth intrinsic mode function and the gas concentration signal; corr() represents the calculation function of the correlation coefficient, and the embodiment of the present invention does not limit the function used when calculating the correlation coefficient; x(t) represents the gas concentration signal; IMF k (t) represents the kth eigenmode function.

[0086] Step S2033, filter out the intrinsic mode functions whose correlation coefficients are greater than a preset threshold. Specifically, a threshold of the correlation coefficient is set according to the requirements and experience of the system. Usually, the setting of the preset threshold needs to take into account the characteristics and noise levels of the signal under different environments. For each intrinsic mode function, if its correlation coefficient is greater than the set threshold, it is considered that the intrinsic mode function mainly contains noise or interference, and it is filtered out and no longer participates in the subsequent signal reconstruction.

[0087] In some optional embodiments, in actual industrial applications, the characteristics of the gas concentration signal will continue to change due to changes in the operating cycle, meteorological conditions, installation location and working conditions. In order to ensure that the embodiments of the present invention continue to maintain high accuracy and stability in a changing environment, the following expansions are made in parameter selection and optimization: First, adaptive adjustment of signal decomposition parameters: Based on the historical data collected at the industrial site and the environmental simulation data, the number of iterations of signal decomposition, the envelope fitting method, the stopping criteria and other parameters are statistically analyzed and dynamically corrected. When the system detects deviations in environmental parameters, such as temperature and humidity, light intensity or vibration level, it automatically calls the corresponding parameter template or uses weighted moving average and other methods to fine-tune the above parameters to better adapt to the current noise characteristics. Second, dynamic setting of correlation coefficient threshold: By analyzing the distribution characteristics of the correlation coefficient under various interference environments, the preset threshold of the correlation coefficient is dynamically optimized through regression models or neural networks and other methods to more accurately screen out highly correlated noise components.

[0088] Step S2034, reconstruct the intrinsic mode functions and residual components that are not filtered out to obtain the target concentration signal corresponding to the gas concentration signal. Specifically, the signal reconstruction is completed using the remaining intrinsic mode functions and residual components after filtering to obtain the reconstructed target concentration signal, which can be expressed by the following formula (3). The reconstructed signal retains the useful information in the original gas concentration signal, while effectively reducing the influence of background noise and interference. By filtering out the intrinsic mode functions that are highly correlated with the background fluctuations, the background fluctuation amplitude of the system is reduced, thereby reducing the interference of the background signal on the detection results, and can effectively suppress the influence of interference signals such as optical interference fringes, improve the purity of the signal, make the reconstructed signal closer to the real gas signal, reduce the possibility of false alarms and missed alarms, thereby significantly improving the detection accuracy of the system, and at the same time enable the system to maintain high stability and reliability in the face of complex and changing environments, meeting high-standard industrial safety monitoring requirements.

[0089]

[0090] in, represents the target concentration signal; K represents the set of intrinsic mode functions that have not been filtered out; r(t) represents the residual component.

[0091] Step S204: constructing a sample database based on the plurality of first target concentration signals and the plurality of second target concentration signals.

[0092] Specifically, the above step S204 includes:

[0093] Step S2041, constructing multiple positive samples based on multiple first target concentration signals.

[0094] In some optional implementations, the above step S2041 includes:

[0095] Step b1, for any first target concentration signal, when there is gas in the standard gas environment and the first target concentration signal indicates the presence of gas, the first target concentration signal is used as a positive sample. Specifically, when there is indeed gas in the standard gas environment and the first target concentration signal also indicates the presence of gas, the first target concentration signal is marked as TP, that is, a positive sample. This indicates that the system has correctly detected the presence of gas. Optionally, when determining whether the target concentration signal indicates the presence of gas, a variety of methods can be used. For example, the target concentration signal is compared with a preset gas concentration. If the signal value exceeds the preset gas concentration, it indicates that gas may be present in the environment; a graph of the gas concentration changing over time is drawn to observe whether there is an obvious peak or a situation where the gas concentration is continuously higher than the preset gas concentration; and the laser absorption spectrum is analyzed to confirm whether there are gas leakage characteristics.

[0096] Step b2, when there is no gas in the standard gas environment and the first target concentration signal indicates that there is no gas, the first target concentration signal is used as a positive-negative sample. Specifically, when there is indeed no gas in the standard gas environment and the first target concentration signal also indicates that there is no gas, the first target concentration signal is marked as TN, i.e., a positive-negative sample. This indicates that the system correctly detects that there is no gas.

[0097] Step b3, taking the positive samples and positive negative samples corresponding to the plurality of first target concentration signals as positive samples. Specifically, collecting all the first target concentration signals marked as positive samples and positive negative samples as the final positive sample set is helpful for system evaluation.

[0098] Step S2042, constructing multiple negative samples based on the multiple second target concentration signals.

[0099] In some optional implementations, the above step S2042 includes:

[0100] Step c1, for any second target concentration signal, when there is no gas in the interference environment corresponding to the second target concentration signal and the second target concentration signal indicates the presence of gas, the second target concentration signal is taken as a negative positive sample. Specifically, when there is actually no gas in the interference environment, but the second target concentration signal indicates the presence of gas, the second target concentration signal is marked as FP, i.e., a negative positive sample. This indicates that the system incorrectly reports the presence of gas, i.e., a false alarm occurs.

[0101] Step c2, when there is gas in the interference environment corresponding to the second target concentration signal and the second target concentration signal indicates that there is no gas, the second target concentration signal is used as a negative sample. Specifically, when there is actually gas in the interference environment, but the second target concentration signal indicates that there is no gas, the second target concentration signal is marked as FN, that is, a negative sample. This indicates that the system has missed the presence of gas under specific interference conditions, that is, a missed detection has occurred.

[0102] Step c3, taking the negative positive samples and negative negative samples corresponding to the plurality of second target concentration signals as negative samples. Specifically, collecting all the second target concentration signals marked as negative positive samples and negative negative samples as the final negative sample set is helpful for system evaluation.

[0103] Step S2043, constructing a sample database based on multiple positive samples and multiple negative samples. Specifically, all positive samples from step S2041 and all negative samples from step S2042 are merged into one database as a basis for subsequent system performance evaluation to achieve a comprehensive evaluation.

[0104] Step S205, based on the sample database, determining the accuracy and false alarm rate of the gas leak detection system during gas detection.

[0105] Specifically, the above step S205 includes:

[0106] Step S2051, for any negative sample in the sample database, if the second target concentration signal corresponding to the negative sample meets the corresponding preset elimination rule, the negative sample is eliminated from the sample database. Specifically, the preset elimination rule can be a concentration error, such as 3%. Since the embodiment of the present invention is carried out under the condition of known gas concentration, that is, whether the concentration signal is collected in a standard gas environment or an interference environment, the gas concentration is known. For any negative sample in the sample database, if the difference between the concentration value represented by the corresponding second target concentration signal and the known gas concentration exceeds 3%, it is eliminated. By eliminating these negative samples, the impact on the evaluation results can be reduced, and the reliability of the accuracy and false alarm rate calculation can be improved.

[0107] Step S2052, the ratio of the number of positive samples in the sample database to the number of all samples in the sample database is used as the accuracy of the gas leak detection system in gas detection. Specifically, the accuracy of the gas leak detection system is determined by the following formula (4), which reflects the correct recognition ability of the system in the overall detection. A high accuracy means that the system can better distinguish the presence and absence of gas.

[0108]

[0109] Among them, Accrtacy represents the accuracy; TP represents the number of positive samples in the positive samples; TN represents the number of positive negative samples in the positive samples; FP represents the number of negative positive samples in the negative samples after removal; FN represents the number of negative negative samples in the negative samples after removal.

[0110] Step S2053, the ratio of the number of positive and negative samples in the sample database to the number of all positive samples in the sample database is used as the false alarm rate of the gas leak detection system during gas detection. Specifically, the false alarm rate of the gas leak detection system can be determined by the following formula (5), which reflects the false alarm probability of the system in the absence of gas. A low false alarm rate means that the system has fewer false alarms.

[0111]

[0112] Among them, FPR represents the false alarm rate; TP represents the number of positive samples in the positive samples; TN represents the number of positive negative samples in the positive samples.

[0113] In some optional embodiments, when it is detected that the system's false alarm rate is high for a long time or there are other trend problems, the parameter retraining and re-optimization process is triggered to update parameters such as the number of signal decomposition iterations and related thresholds to ensure the long-term adaptability and stability of the system.

[0114] The performance evaluation method of the gas leak detection system provided in the embodiment of the present invention collects multiple first gas concentration signals and multiple second gas concentration signals in the target area by using the gas leak detection system in a standard gas environment and an interference environment respectively. It not only takes into account the standard laboratory environment, but also introduces multiple interference environments, and can simulate various complex situations that may be encountered in actual applications, so that the evaluation result is closer to the real scene, thereby improving the practicality and credibility of the evaluation. By decomposing and reconstructing the above-collected gas concentration signal, the background noise and interference signal in the signal can be effectively removed, so that the target concentration signal is purer, and the accuracy of subsequent data analysis is improved. Through the target concentration signals under different environments, a comprehensive and diverse sample database is constructed, which can better reflect the performance of the system under various environmental conditions, so that the accuracy rate and false alarm rate are calculated based on the sample database, so that the performance evaluation of the system is more scientific and rigorous, and the reliability and trustworthiness of the system are enhanced. Not only the performance under an ideal environment is considered, but also the performance under a complex interference environment is paid special attention to, so that the evaluation result is more in line with the actual application scenario.

[0115] In this embodiment, a performance evaluation device for a gas leak detection system is also provided, which is used to implement the above-mentioned embodiments and preferred implementation modes, and will not be repeated hereafter. As used below, the term "module" may be a combination of software and / or hardware that implements a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceivable.

[0116] This embodiment provides a performance evaluation device for a gas leak detection system. Figure 2 As shown, including:

[0117] The first acquisition module 201 is used to acquire a plurality of first gas concentration signals in a target area by using a gas leak detection system under a standard gas environment.

[0118] The second acquisition module 202 is used to respectively acquire a plurality of second gas concentration signals in a target area by using a gas leak detection system under various interference environments.

[0119] The signal processing module 203 is used to perform signal decomposition and reconstruction on the multiple first gas concentration signals and the multiple second gas concentration signals respectively to obtain multiple first target concentration signals and multiple second target concentration signals, wherein the background noise and interference signal of the target concentration signal are less than those of the corresponding gas concentration signal.

[0120] The construction module 204 is used to construct a sample database based on the multiple first target concentration signals and the multiple second target concentration signals.

[0121] The evaluation module 205 is used to determine the accuracy and false alarm rate of the gas leak detection system during gas detection based on the sample database.

[0122] In some optional implementations, the signal processing module 203 includes:

[0123] The decomposition unit is used for decomposing any gas concentration signal into a residual component and a plurality of intrinsic mode functions.

[0124] The calculation unit is used to calculate the correlation coefficient between the gas concentration signal and each intrinsic mode function.

[0125] The filtering unit is used to filter out the intrinsic mode functions whose correlation coefficients are greater than a preset threshold.

[0126] The reconstruction unit is used to reconstruct the intrinsic mode function and residual component that are not filtered out to obtain a target concentration signal corresponding to the gas concentration signal.

[0127] In some optional embodiments, the decomposition unit comprises:

[0128] The first determination subunit is used to determine the local maximum point and the local minimum point of the gas concentration signal.

[0129] The fitting subunit is used to obtain the upper envelope and the lower envelope by using the cubic spline interpolation method based on the local maximum point and the local minimum point.

[0130] The calculation subunit is used to calculate the average value of the upper envelope and the lower envelope to obtain the mean envelope.

[0131] The second determination subunit is used to determine the difference between the gas concentration signal and the mean envelope. When the difference does not meet the decomposition requirements, the difference is used as the gas concentration signal for the next decomposition, and the process returns to the step of determining the local maximum and local minimum points of the gas concentration signal until the difference meets the decomposition requirements, and the difference is used as the intrinsic mode function of this decomposition.

[0132] The third determination subunit is used to take the difference between the gas concentration signal and all the intrinsic mode functions as the residual component of this decomposition.

[0133] The fourth determination subunit is used to use the residual component of this decomposition as the gas concentration signal for the next decomposition, and return to the step of determining the local maximum points and local minimum points of the gas concentration signal, until the sum of the number of local maximum points and local minimum points of the residual component of this decomposition is less than a preset number threshold, so as to obtain the final residual component.

[0134] In some optional implementations, the construction module 204 includes:

[0135] The first construction unit is used to construct a plurality of positive samples based on a plurality of first target concentration signals.

[0136] The second construction unit is used to construct multiple negative samples based on multiple second target concentration signals.

[0137] The third construction unit is used to construct a sample database based on multiple positive samples and multiple negative samples.

[0138] In some optional embodiments, the first building block includes:

[0139] The fifth determination subunit is configured to, for any first target concentration signal, take the first target concentration signal as a positive sample when there is gas in the standard gas environment and the first target concentration signal indicates the presence of gas.

[0140] The sixth determination subunit is used to use the first target concentration signal as a positive-negative sample when there is no gas in the standard gas environment and the first target concentration signal indicates that there is no gas.

[0141] The first construction subunit is used to take the positive-positive samples and the positive-negative samples corresponding to the plurality of first target concentration signals as positive samples.

[0142] In some optional embodiments, the second building block includes:

[0143] The seventh determination subunit is used to, for any second target concentration signal, take the second target concentration signal as a negative positive sample when there is no gas in the interference environment corresponding to the second target concentration signal and the second target concentration signal indicates the presence of gas.

[0144] The eighth determination subunit is configured to use the second target concentration signal as a negative sample when there is gas in the interference environment corresponding to the second target concentration signal and the second target concentration signal indicates that there is no gas.

[0145] The second construction subunit is used to use the negative positive samples and negative negative samples corresponding to the multiple second target concentration signals as negative samples.

[0146] In some optional implementations, the evaluation module 205 includes:

[0147] The elimination unit is used to eliminate any negative sample in the sample database from the sample database when the second target concentration signal corresponding to the negative sample meets the corresponding preset elimination rule.

[0148] The first evaluation unit is used to use the ratio of the number of positive samples in the sample database to the number of all samples in the sample database as the accuracy of the gas leak detection system during gas detection.

[0149] The second evaluation unit is used to use the ratio of the number of positive and negative samples in the sample database to the number of all positive samples in the sample database as the false alarm rate of the gas leak detection system during gas detection.

[0150] The further functional description of each of the above modules and units is the same as that of the above corresponding embodiments and will not be repeated here.

[0151] The performance evaluation device of the gas leak detection system in this embodiment is presented in the form of a functional unit, where the unit refers to an ASIC (Application Specific Integrated Circuit) circuit, a processor and memory that executes one or more software or fixed programs, and / or other devices that can provide the above functions.

[0152] The embodiment of the present invention also provides a computer device having the above Figure 2 The performance evaluation device of the gas leak detection system shown.

[0153] See also Figure 3 , Figure 3 is a schematic diagram of the structure of a computer device provided by an optional embodiment of the present invention, such as Figure 3 As shown, the computer device includes: one or more processors 10, a memory 20, and interfaces for connecting various components, including high-speed interfaces and low-speed interfaces. Various components are connected to each other using different buses for communication, and can be installed on a common mainboard or installed in other ways as needed. The processor can process the instructions executed in the computer device, including instructions stored in or on the memory to display the graphical information of the GUI on an external input / output device (such as, a display device coupled to the interface). In some optional embodiments, if necessary, multiple processors and / or multiple buses can be used together with multiple memories and multiple memories. Similarly, multiple computer devices can be connected, and each device provides some necessary operations (for example, as a server array, a group of blade servers, or a multi-processor system). Figure 3A processor 10 is taken as an example.

[0154] The processor 10 may be a central processing unit, a network processor or a combination thereof. The processor 10 may further include a hardware chip. The hardware chip may be a dedicated integrated circuit, a programmable logic device or a combination thereof. The programmable logic device may be a complex programmable logic device, a field programmable gate array, a general purpose array logic or any combination thereof.

[0155] The memory 20 stores instructions executable by at least one processor 10, so that at least one processor 10 executes the method shown in the above embodiment.

[0156] The memory 20 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created according to the use of the computer device, etc. In addition, the memory 20 may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage device. In some optional embodiments, the memory 20 may optionally include a memory remotely arranged relative to the processor 10, and these remote memories may be connected to the computer device via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0157] The memory 20 may include a volatile memory, such as a random access memory; the memory may also include a non-volatile memory, such as a flash memory, a hard disk or a solid state drive; the memory 20 may also include a combination of the above types of memory.

[0158] The computer device also includes an input device 30 and an output device 40. The processor 10, the memory 20, the input device 30 and the output device 40 may be connected via a bus or other means. Figure 3 The example of connecting through bus is taken in the following.

[0159] The input device 30 can receive input digital or character information, and generate key signal input related to the user settings and function control of the computer device, such as a touch screen, a keypad, a mouse, a track pad, a touch pad, an indicator bar, one or more mouse buttons, a trackball, a joystick, etc. The output device 40 may include a display device, an auxiliary lighting device (e.g., an LED) and a tactile feedback device (e.g., a vibration motor), etc. The above-mentioned display device includes but is not limited to a liquid crystal display, a light emitting diode, a display and a plasma display. In some optional embodiments, the display device can be a touch screen.

[0160] The embodiment of the present invention also provides a computer-readable storage medium. The method according to the embodiment of the present invention can be implemented in hardware, firmware, or can be implemented as a computer code that can be recorded in a storage medium, or can be implemented as a computer code that is originally stored in a remote storage medium or a non-temporary machine-readable storage medium and will be stored in a local storage medium through a network download, so that the method described herein can be stored in such software processing on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. Among them, the storage medium can be a magnetic disk, an optical disk, a read-only storage memory, a random access memory, a flash memory, a hard disk or a solid-state hard disk, etc.; further, the storage medium can also include a combination of the above types of memories. It can be understood that a computer, a processor, a microprocessor controller, or programmable hardware includes a storage component that can store or receive software or computer code. When the software or computer code is accessed and executed by a computer, a processor, or hardware, the method shown in the above embodiment is implemented.

[0161] A part of the present invention may be applied as a computer program product, such as a computer program instruction, which, when executed by a computer, can call or provide the method and / or technical solution according to the present invention through the operation of the computer. Those skilled in the art should understand that the existence of the computer program instruction in a computer-readable medium includes, but is not limited to, a source file, an executable file, an installation package file, etc., and accordingly, the way in which the computer program instruction is executed by the computer includes, but is not limited to: the computer directly executes the instruction, or the computer compiles the instruction and then executes the corresponding compiled program, or the computer reads and executes the instruction, or the computer reads and installs the instruction and then executes the corresponding installed program. Here, the computer-readable medium may be any available computer-readable storage medium or communication medium accessible to the computer.

[0162] Although the embodiments of the present invention have been described in conjunction with the accompanying drawings, those skilled in the art may make various modifications and variations without departing from the spirit and scope of the present invention, and such modifications and variations are all within the scope defined by the appended claims.

Claims

1. A performance evaluation method for a gas leak detection system, characterized in that: The method comprises: Under a standard gas environment, a gas leak detection system is used to collect a plurality of first gas concentration signals in a target area; Under various interference environments, the gas leak detection system is used to collect a plurality of second gas concentration signals in the target area respectively; Performing signal decomposition and reconstruction on the plurality of first gas concentration signals and the plurality of second gas concentration signals respectively to obtain a plurality of first target concentration signals and a plurality of second target concentration signals, wherein the background noise and interference signal of the target concentration signals are less than the corresponding gas concentration signals; constructing a sample database based on the plurality of first target concentration signals and the plurality of second target concentration signals; Based on the sample database, the accuracy and false alarm rate of the gas leak detection system during gas detection are determined.

2. The method according to claim 1, characterized in that The performing signal decomposition and reconstruction on the plurality of first gas concentration signals and the plurality of second gas concentration signals respectively to obtain a plurality of first target concentration signals and a plurality of second target concentration signals comprises: For any gas concentration signal, decomposing the gas concentration signal into a residual component and a plurality of intrinsic mode functions; Calculating the correlation coefficient between the gas concentration signal and each intrinsic mode function; Filter out the intrinsic mode functions whose correlation coefficients are greater than a preset threshold; The unfiltered intrinsic mode function and the residual component are reconstructed to obtain a target concentration signal corresponding to the gas concentration signal.

3. The method according to claim 2, characterized in that For any gas concentration signal, decomposing the gas concentration signal into a residual component and a plurality of intrinsic mode functions includes: Determining the local maximum point and the local minimum point of the gas concentration signal; Based on the local maximum point and the local minimum point, an upper envelope and a lower envelope are obtained by fitting using a cubic spline interpolation method; Calculating the average value of the upper envelope and the lower envelope to obtain a mean envelope; Determine the difference between the gas concentration signal and the mean envelope, and if the difference does not meet the decomposition requirement, use the difference as the gas concentration signal for next decomposition, and return to the step of determining the local maximum point and the local minimum point of the gas concentration signal until the difference meets the decomposition requirement, and use the difference as the intrinsic mode function of this decomposition; The difference between the gas concentration signal and all intrinsic mode functions is used as the residual component of this decomposition; The residual component of this decomposition is used as the gas concentration signal for the next decomposition, and the process returns to the step of determining the local maximum points and local minimum points of the gas concentration signal, until the sum of the number of local maximum points and local minimum points of the residual component of this decomposition is less than the preset number threshold, and the final residual component is obtained.

4. The method according to claim 1, characterized in that: The constructing a sample database based on the plurality of first target concentration signals and the plurality of second target concentration signals comprises: constructing a plurality of positive samples based on the plurality of first target concentration signals; constructing a plurality of negative samples based on the plurality of second target concentration signals; The sample database is constructed based on the multiple positive samples and the multiple negative samples.

5. The method according to claim 4, characterized in that The step of constructing a plurality of positive samples based on the plurality of first target concentration signals comprises: For any first target concentration signal, when there is gas in the standard gas environment and the first target concentration signal indicates the presence of gas, the first target concentration signal is taken as a positive sample; When there is no gas in the standard gas environment and the first target concentration signal indicates that there is no gas, taking the first target concentration signal as a positive and negative sample; The positive samples and the positive negative samples corresponding to the multiple first target concentration signals are taken as the positive samples.

6. The method according to claim 5, characterized in that The step of constructing a plurality of negative samples based on the plurality of second target concentration signals comprises: For any second target concentration signal, when there is no gas in the interference environment corresponding to the second target concentration signal and the second target concentration signal indicates the presence of gas, the second target concentration signal is taken as a negative positive sample; When there is gas in the interference environment corresponding to the second target concentration signal and the second target concentration signal indicates that there is no gas, taking the second target concentration signal as a negative sample; The negative positive samples and negative negative samples corresponding to the multiple second target concentration signals are used as the negative samples.

7. The method according to claim 6, characterized in that The step of determining the accuracy and false alarm rate of the gas leak detection system during gas detection based on the sample database includes: For any negative sample in the sample database, if the second target concentration signal corresponding to the negative sample satisfies the corresponding preset elimination rule, the negative sample is eliminated from the sample database; The ratio of the number of positive samples in the sample database to the number of all samples in the sample database is used as the accuracy of the gas leak detection system in gas detection; The ratio of the number of positive and negative samples in the sample database to the number of all positive samples in the sample database is used as the false alarm rate of the gas leak detection system during gas detection.

8. A performance evaluation device for a gas leak detection system, characterized in that: The device comprises: A first acquisition module is used to acquire a plurality of first gas concentration signals in a target area using a gas leak detection system under a standard gas environment; A second acquisition module is used to respectively acquire a plurality of second gas concentration signals in the target area using the gas leak detection system under various interference environments; a signal processing module, configured to perform signal decomposition and reconstruction on the plurality of first gas concentration signals and the plurality of second gas concentration signals respectively, to obtain a plurality of first target concentration signals and a plurality of second target concentration signals, wherein the background noise and interference signal of the target concentration signals are less than the corresponding gas concentration signals; A construction module, configured to construct a sample database based on the plurality of first target concentration signals and the plurality of second target concentration signals; An evaluation module is used to determine the accuracy and false alarm rate of the gas leak detection system during gas detection based on the sample database.

9. A computer device, characterized in that: include: A memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the performance evaluation method of the gas leak detection system according to any one of claims 1 to 7 by executing the computer instructions.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a computer to execute the performance evaluation method of the gas leak detection system according to any one of claims 1 to 7.

Images