Fire-fighting equipment detection method, system and device and storage medium

Abstract

The invention relates to the technical field of fire-fighting equipment detection, and discloses a fire-fighting equipment detection method, system and device and a storage medium. The method comprises the following steps: in the working process of to-be-detected fire fighting equipment, acquiring equipment type and working parameter data acquired from the to-be-detected fire fighting equipment; according to the equipment type and the working parameter data, data extraction operation is carried out to obtain sample data, and the sample data comprises known parameter data and a detection result; performing feature mapping operation according to the sample data to obtain a feature space; performing kernel skill calculation operation according to the feature space, the working parameter data and the sample data to obtain data similarity; and according to the data similarity, performing similarity matching operation to obtain a fire-fighting equipment detection result. According to the invention, the fire-fighting equipment can be detected, and the detection accuracy is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of fire-fighting equipment detection, and in particular to a fire-fighting equipment detection method, system, device and storage medium. Background Art

[0002] At present, with the popularization of various electronic devices, the probability of fire has increased. Firefighting equipment is a direct means of disaster reduction directly facing users. The performance of firefighting equipment is closely related to fire safety. It is an important firefighting facility to ensure the safety of people and property. According to different firefighting needs, the design and process of firefighting products vary greatly. At present, facing various application scenarios, my country's firefighting products have formulated corresponding standards before production, and these standards have played an important role in restraining and guiding actual production. However, there are still some defects in the existing firefighting product certification system, especially the lack of daily supervision and testing of product and component performance, which easily leads to uneven quality of firefighting products and seriously restricts the improvement of firefighting product quality. Existing firefighting products are usually tested by testing. For example, high-voltage firefighting products can be tested on-site and type tested, some firefighting products can be tested on-site and type tested, and most firefighting products only need to be type tested according to the standard.

[0003] Traditional testing methods are mainly carried out through sampling testing, which has high testing costs and limited coverage. Therefore, it is difficult to detect all fire protection products. In addition, the number of samples for sampling testing is limited, and the statistical characteristics of sample data are limited. It is impossible to use the completeness of sample data to improve the accuracy of testing. Although the existing fire protection product testing technology can provide support for the comprehensive quality management of fire protection products. However, with the increase in product types and models, it brings huge technical challenges to the testing of fire protection products. At the same time, with the development of new products, the structure and function of products tend to be complex, which also puts forward new requirements for the accuracy of product testing methods. In the process of product manufacturing, due to reasons such as manufacturing raw materials and manufacturing processes, there are certain differences between individual products. The existing technology cannot carry out targeted testing of different individual products based on this difference. In the process of product manufacturing, due to batch problems or the change of raw material batches during the manufacturing process, the performance of products from different batches is different. The existing technology does not detect and identify the performance of such different batches of products.

[0004] Therefore, the above methods limit the detection accuracy. Especially in today's society where product structures change rapidly, the above detection technologies cannot perform effective and accurate detection. Summary of the invention

[0005] The present invention provides a fire-fighting equipment detection method, system, device and storage medium to realize the detection of fire-fighting equipment and improve the detection accuracy.

[0006] In a first aspect, in order to solve the above technical problems, the present invention provides a fire fighting equipment detection method, comprising:

[0007] During the operation of the fire-fighting equipment to be detected, obtaining equipment type and operating parameter data collected from the fire-fighting equipment to be detected;

[0008] Performing a data extraction operation according to the device type and the working parameter data to obtain sample data, wherein the sample data includes known parameter data and a test result;

[0009] Performing a feature mapping operation according to the sample data to obtain a feature space;

[0010] Performing a kernel skill calculation operation according to the feature space, the working parameter data and the sample data to obtain data similarity;

[0011] A similarity matching operation is performed based on the data similarity to obtain a fire-fighting equipment detection result.

[0012] As an optional implementation manner, before performing a feature mapping operation according to the sample data to obtain a feature space, the method further includes:

[0013] Preprocessing and analyzing operations are performed according to the sample data to obtain sample processing data.

[0014] As an optional implementation manner, performing preprocessing and analysis operations according to the sample data to obtain sample processing data includes:

[0015] According to the sample data, an abnormal data cleaning operation is performed to obtain denoised data, wherein the denoised data includes denoised known parameter data and denoised detection results;

[0016] A principal component analysis operation is performed based on the known parameter data after denoising to obtain sample processing data.

[0017] As an optional implementation manner, performing a feature mapping operation according to the sample data to obtain a feature space includes:

[0018] A feature mapping operation is performed based on the known parameter data after denoising and the detection result after denoising to obtain the feature space, wherein the known parameter data after denoising serves as the input parameter of the feature space, and the detection result after denoising serves as the output parameter of the feature space, the known parameter data after denoising includes the length of the water hose, the cross-sectional radius of the pipe joints at both ends, the cross-sectional area and the wall thickness of the water hose, and the detection result after denoising includes the bursting pressure of the water hose.

[0019] As an optional implementation, the feature mapping operation is an operation of establishing a nonlinear regression model using a support vector machine kernel function, including:

[0020] The operating formula for establishing a nonlinear regression model is:

[0021]

[0022] Among them, K(x i , x j ) is the support vector machine kernel function; x i is the i-th sample data, x j is the jth sample data, ||x i -x j || is x i With x j The Euclidean distance between them, ∈ and σ are support vector machine kernel function parameters, and the support vector machine kernel function parameters ∈ and σ are determined by cross-validation method.

[0023] As an optional implementation manner, performing a kernel skill calculation operation according to the feature space, the working parameter data and the sample data to obtain data similarity includes:

[0024] The kernel trick calculation operation formula is:

[0025] rij=K(bij,bi)

[0026] Among them, bij is the working parameter data, bi is the sample data, K is the support vector machine kernel function of the feature space, and rij is the data similarity.

[0027] As an optional implementation manner, performing a similarity matching operation according to the data similarity to obtain a fire equipment detection result includes:

[0028] If the denoised detection result matches the fire-fighting equipment to be detected, a similarity matching operation is performed;

[0029] If the denoising detection result does not match the fire-fighting equipment to be detected, an abnormal data judgment operation is performed; if abnormal data exists, a new feature space is established based on the fire-fighting equipment to be detected, and a similarity matching operation is performed; if abnormal data does not exist, a database addition operation is performed based on the sample data of the fire-fighting equipment to be detected.

[0030] As an optional implementation manner, it is characterized in that the similarity matching operation is performed according to the data similarity to obtain the fire equipment detection result, including:

[0031] If rij>s, the fire-fighting equipment to be detected corresponding to the sample data is qualified; if rij≤s, the fire-fighting equipment to be detected corresponding to the sample data is unqualified, wherein s is the preset detection threshold and rij is the data similarity.

[0032] In a second aspect, the present invention provides a fire equipment detection system, comprising:

[0033] A data acquisition module, used to acquire equipment type and working parameter data collected from the fire-fighting equipment to be detected during its operation;

[0034] A data extraction module, used to perform a data extraction operation according to the device type and the working parameter data to obtain sample data, wherein the sample data includes known parameter data and a test result;

[0035] A feature space obtaining module, used for performing a feature mapping operation according to the sample data to obtain a feature space;

[0036] A similarity calculation module, used to perform a kernel skill calculation operation according to the feature space, the working parameter data and the sample data to obtain data similarity;

[0037] The similarity matching module is used to perform a similarity matching operation according to the data similarity to obtain a fire-fighting equipment detection result.

[0038] In a third aspect, the present invention provides a device, characterized in that it includes a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, it implements the fire equipment detection method described above.

[0039] In a fourth aspect, the present invention also provides a computer-readable storage medium, characterized in that the computer-readable storage medium includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the fire equipment detection method as described above.

[0040] Compared with the prior art, the present invention has the following beneficial effects:

[0041] The present invention provides a fire-fighting equipment detection method, comprising: obtaining the equipment type and working parameter data collected from the fire-fighting equipment to be detected during its operation; performing a data extraction operation according to the equipment type and the working parameter data to obtain sample data, wherein the sample data includes known parameter data and a detection result; performing a feature mapping operation according to the sample data to obtain a feature space; performing a kernel technique calculation operation according to the feature space, the working parameter data and the sample data to obtain data similarity; performing a similarity matching operation according to the data similarity to obtain a fire-fighting equipment detection result.

[0042] In the present invention, by testing the fire-fighting equipment, the following advantages are achieved: the test results are accurate and the test efficiency is high; there is no need to simulate extreme environments multiple times, and sufficient data can be obtained by one test, which greatly saves the test cost; it can be applied to a variety of fire-fighting equipment, and has strong applicability and comprehensiveness; the fire-fighting equipment is automated and batched through the measuring equipment, so as to avoid human measurement errors and improve the test efficiency and accuracy; the fire-fighting equipment cost is reduced and the effectiveness of the fire-fighting equipment test is guaranteed; the clamping device for clamping the water hose can be automatically adjusted according to different water hose diameters and lengths, and the operation is convenient and fast. The specific test process is: in the process of the fire-fighting equipment to be tested, the equipment type and working parameter data collected from the fire-fighting equipment to be tested are obtained. Then, a data extraction operation is performed according to the equipment type and the working parameter data to obtain sample data, and the sample data includes known parameter data and test results. Then, a feature mapping operation is performed on the sample data to obtain a feature space. Then, according to the feature space, the working parameter data and the sample data, a kernel skill calculation operation is performed to obtain the similarity between the working parameter data and the sample data. Finally, a similarity matching operation is performed according to the similarity to obtain the fire-fighting equipment test result. The fire-fighting equipment can be inspected according to the above method. No manual measurement and data analysis is required in the whole process, thus avoiding human measurement errors and significantly improving the inspection accuracy of the fire-fighting equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] Figure 1 It is a flowchart of a fire-fighting equipment detection method provided by an embodiment of the present invention;

[0044] Figure 2 It is a structural schematic diagram of a fire-fighting equipment detection system provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0045] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0046] It should be noted that with the popularization of various electronic devices, the probability of fire has increased, and fire-fighting equipment is a direct means of disaster reduction directly facing users. The performance of fire-fighting equipment is closely related to fire safety. It is an important fire-fighting facility to ensure the safety of people and property. According to different fire-fighting needs, the design and process of fire-fighting products vary greatly. At present, facing various application scenarios, my country's fire-fighting products have formulated corresponding standards before production, and these standards have played an important role in restraining and guiding actual production. However, there are still some defects in the existing fire-fighting product certification system, especially the lack of daily supervision and testing of product and component performance, which easily leads to uneven quality of fire-fighting products and seriously restricts the improvement of fire-fighting product quality. Existing fire-fighting products are usually tested by testing. For example, high-voltage fire-fighting products can be tested on-site and type tests, some fire-fighting products can be tested on-site and type tests, and most fire-fighting products only need to be type tested in accordance with standard regulations. Traditional testing methods are mainly carried out through sampling testing, which has high testing costs and limited coverage. Therefore, it is difficult to detect all fire protection products. In addition, the number of samples for sampling testing is limited, and the statistical characteristics of sample data are limited. It is impossible to use the completeness of sample data to improve the accuracy of detection. Although the existing fire protection product detection technology can provide support for the comprehensive quality management of fire protection products. However, with the increase in product types and models, it brings huge technical challenges to the detection of fire protection products. At the same time, with the development of new products, the structure and function of products tend to be complex, which also puts forward new requirements for the accuracy of product testing methods. In the product manufacturing process, due to reasons such as manufacturing raw materials and manufacturing processes, there are certain differences between individual products. The existing technology cannot perform targeted detection on different individual products based on this difference. In the product manufacturing process, some products have certain differences in performance due to batch problems or the replacement of raw material batches during the manufacturing process. The existing technology does not detect and identify the performance of such different batches of products. Therefore, the above methods limit the detection accuracy. Especially in today's society where product structure changes rapidly, the above detection technology cannot perform effective and accurate detection.

[0047] For the above problems, refer to Figure 1 The first embodiment of the present invention provides a fire fighting equipment detection method, comprising the following steps:

[0048] S11, during the operation of the fire-fighting equipment to be detected, obtaining equipment type and operating parameter data collected from the fire-fighting equipment to be detected;

[0049] S12, performing a data extraction operation according to the device type and the working parameter data to obtain sample data, wherein the sample data includes known parameter data and a test result;

[0050] S13, performing a feature mapping operation according to the sample data to obtain a feature space;

[0051] S14, performing a kernel skill calculation operation according to the feature space, the working parameter data and the sample data to obtain data similarity;

[0052] S15, performing a similarity matching operation according to the data similarity to obtain a fire-fighting equipment detection result.

[0053] In step S11, during the operation of the fire-fighting equipment to be detected, the equipment type and operating parameter data collected from the fire-fighting equipment to be detected are obtained.

[0054] In the above embodiment, the fire-fighting equipment can collect detailed information about the equipment type in real time through built-in sensors and monitoring systems, including important parameters such as the length and material of the hose. This process ensures a comprehensive understanding of the status of the fire-fighting equipment, while providing a reliable data basis for subsequent performance analysis and safety inspections. In addition, the fire-fighting equipment also has the function of recording real-time working parameters, such as key data such as pressure, flow and temperature. This information is not only used to evaluate the operating effect of the equipment, but also to detect potential problems in a timely manner, thereby ensuring the effectiveness and safety in actual fire-fighting operations. In this way, fire-fighting equipment can be better detected and managed to improve the overall level of fire safety.

[0055] It should be specifically stated that the fire-fighting equipment includes water hoses, and the types to be tested mainly include parameters such as the length and material of the water hoses. These parameters are crucial for evaluating the performance of the water hoses during actual use. By systematically testing and analyzing water hoses of different lengths and materials, we can fully understand their characteristics in terms of pressure bearing, wear resistance and flexibility, and provide a scientific basis for subsequent optimization design and application. The detection method of the present invention is intended to ensure the safety and reliability of various types of water hoses in actual fire-fighting applications, thereby improving the overall working efficiency and emergency response capabilities of fire-fighting equipment.

[0056] It should also be specified that, according to the classification of fire protection products, fire protection equipment can usually be divided into three categories: automatic fire alarm control equipment, fire linkage control equipment and fire protection facilities. Among them, automatic fire alarm control equipment includes fire detectors, manual alarm buttons, fire hydrants, hydraulic, electrical fire detectors, fire dampers, smoke exhaust systems, fire alarms and fire control equipment; fire linkage control equipment covers gas fire extinguishing systems, fire doors and smoke exhaust systems; and fire protection facilities include fire extinguishers, fire water monitors, fire pools and fire pumps. In order to ensure the performance and safety of the fire protection equipment to be tested, it is necessary to first clarify the type of the equipment and obtain its working parameter data accordingly. These data include but are not limited to key indicators such as equipment name, manufacturer, technical parameters, temperature, vibration, acceleration, current, speed, pressure, etc. The collection and analysis of this series of data provides an important basis for subsequent performance evaluation and fault diagnosis, and helps to improve the overall reliability and effectiveness of fire protection equipment.

[0057] In step S12, a data extraction operation is performed according to the device type and the working parameter data to obtain sample data, wherein the sample data includes known parameter data and detection results.

[0058] In the above embodiment, these known parameter data represent the standard operating indicators of fire-fighting equipment, and the test results are performance evaluations obtained after in-depth analysis of real-time collected data. By sorting and comparing these sample data, the operating status of fire-fighting equipment can be effectively identified, and possible deviations or abnormalities can be discovered in time, which provides an important basis for subsequent maintenance and improvement. This systematic data analysis can not only help to establish a more accurate equipment performance model, but also bring significant improvements to future detection work. More importantly, with the continuous optimization of this process, the accuracy and efficiency of detection will be significantly improved, ensuring that the equipment is always in the best condition and reducing the risk of failure. Through this method, not only can we respond to emergencies in a timely manner, but we can also achieve more efficient resource allocation in daily management, laying a solid foundation for ensuring fire safety. In short, the in-depth analysis and application of sample data will bring continuous improvement and innovation to the management and maintenance of fire-fighting equipment.

[0059] It should be specifically explained that, according to the type of fire-fighting equipment to be detected, it is first necessary to query the parameter data of various types and models of fire-fighting equipment stored in the database. These data not only include the basic information of the equipment, but also cover important data such as the environmental conditions and related parameters allowed for the operation of the fire-fighting equipment. After completing this query, the sample data in the database will be compared based on the current parameter data of the fire-fighting equipment to be detected obtained in step S11 to confirm whether there is corresponding matching data. In the comparison process, the sample data that is closest to and matches the current parameter data of the fire-fighting equipment to be detected obtained in step S11 will be selected, and these sample data will be used as the basis for prediction. Generally speaking, these sample data include equipment name, manufacturer, technical parameters, and multiple key indicators such as temperature, vibration, acceleration, current and speed. In addition, the sample data also includes test result data obtained by simulating extreme environmental conditions. This systematic query and comparison process will help to more accurately evaluate the performance of the equipment to be detected and provide a scientific basis for subsequent maintenance and optimization.

[0060] In step S13, a feature mapping operation is performed according to the sample data to obtain a feature space.

[0061] In one embodiment, before performing a feature mapping operation on the sample data to obtain a feature space, the method further includes: performing a preprocessing and analysis operation on the sample data to obtain sample processing data.

[0062] In one embodiment, the preprocessing and analysis operations are performed based on the sample data to obtain sample processing data, including: performing an abnormal data cleaning operation based on the sample data to obtain denoised data, wherein the denoised data includes denoised known parameter data and denoised detection results; performing a principal component analysis operation based on the denoised known parameter data to obtain sample processing data.

[0063] In the above embodiment, by performing a multi-dimensional in-depth analysis of the known parameters and test results in the sample data, the present invention can effectively extract key features, including the response time, failure rate and work efficiency of the equipment. These features are then converted into feature space by establishing a mathematical model or applying a corresponding algorithm, so that different types of fire-fighting equipment and their performance indicators can be systematically compared and analyzed in a unified feature space. The construction of the feature space not only provides a solid theoretical foundation for subsequent pattern recognition and intelligent decision-making, but also significantly improves the accuracy and efficiency of equipment detection. The implementation of this analysis method enables a more comprehensive understanding of equipment performance, helps to optimize detection strategies, and further improves the operational safety of fire-fighting equipment, thereby providing strong technical support for the development of related fields.

[0064] Exemplarily, the feature mapping operation is an operation of establishing a nonlinear regression model using a support vector machine kernel function, including: the formula for establishing the nonlinear regression model operation is:

[0065]

[0066] Among them, K(x i , x j ) is the support vector machine kernel function; x i is the i-th sample data, x j is the jth sample data, ||x i -x j || is x i With x j The Euclidean distance between them, ∈ and σ are support vector machine kernel function parameters, and the support vector machine kernel function parameters ∈ and σ are determined by cross-validation method.

[0067] In step S14, a kernel technique calculation operation is performed according to the feature space, the working parameter data and the sample data to obtain data similarity.

[0068] In one implementation, performing a kernel skill calculation operation according to the feature space, the working parameter data, and the sample data to obtain data similarity includes: the kernel skill calculation operation formula is:

[0069] rij=K(bij,bi)

[0070] Among them, bij is the working parameter data, bi is the sample data, K is the support vector machine kernel function of the feature space, and rij is the data similarity.

[0071] In the above embodiment, by applying the kernel technique method, the data points in the high-dimensional feature space can be effectively mapped to a low-dimensional space that is more suitable for similarity calculation. This technology can handle complex data structures, making the comparison between different samples more intuitive and efficient. The process is based on the extracted features and working parameter data, and the inner product between each sample is calculated to obtain a similarity index. These similarity values ​​can not only help identify equipment with similar performance, but also timely discover potential faulty equipment, thereby optimizing the management and maintenance strategy of the equipment. In this way, the overall safety and reliability of fire-fighting equipment can be significantly improved to ensure the normal operation of the equipment. At the same time, this improved method can also improve the accuracy of fire-fighting equipment detection, provide strong data support for daily maintenance, and reduce the risks brought by equipment failure.

[0072] It should be specifically explained that in the above method, preprocessing steps such as denoising and principal component analysis are used to effectively process sample data of fire-fighting equipment of different types, batches and models. Through these preprocessing steps, the quality and consistency of the data can be significantly improved, laying the foundation for subsequent analysis. Based on the support vector machine to construct a feature space, the present invention introduces the preprocessed sample data into the established feature space. In this feature space, by performing calculations and analysis on the current parameter data and the known data in the database, the detection results of the corresponding type of fire-fighting equipment can be accurately obtained. This method not only improves the accuracy of detection, but also enhances the ability to compare and evaluate the performance of different equipment, thereby providing a more scientific basis for the intelligent detection and management of fire-fighting equipment.

[0073] It should be specifically noted that if the adopted support vector machine fails to meet the processing requirements, its kernel parameters need to be adjusted accordingly, and step 13 is re-executed to optimize the model performance. After adjustment, the performance of the support vector machine is evaluated again to ensure that it can effectively process the input data. If the adjusted support vector machine meets the preset processing standards, the similarity calculation result will be output and step 15 will be continued. This feedback mechanism not only ensures the adaptability and accuracy of the algorithm, but also provides reliable data support for further analysis and decision-making, thereby improving the efficiency and intelligence level of the overall system.

[0074] It is also necessary to specify that the support vector machine technology of the present invention is widely applicable to the detection of various types of fire-fighting equipment, including but not limited to automatic fire alarm control equipment, fire linkage control equipment, various types of fire-fighting facilities, fire detectors, manual alarm buttons, fire hydrants, hydraulic and electrical fire detectors, fire dampers, smoke exhaust systems, fire alarms, fire control equipment, gas fire extinguishing systems and fire doors, etc. By conducting an in-depth analysis of the working conditions of these devices under simulated extreme environments, the present invention can obtain relevant parameter data and perform precise calculation and analysis on it with the sample data stored in the database, so as to comprehensively evaluate the working performance of the fire-fighting equipment and realize an efficient and accurate detection process. The present invention not only has the advantages of simple operation and high reliability, but also can effectively adapt to the detection needs of different types of fire-fighting equipment, providing important technical support for fire safety management.

[0075] In step S15, a similarity matching operation is performed according to the data similarity to obtain a fire equipment detection result.

[0076] In one embodiment, the similarity matching operation is performed based on the data similarity to obtain the fire equipment detection result, including: if the denoised detection result matches the fire equipment to be detected, a similarity matching operation is performed; if the denoised detection result does not match the fire equipment to be detected, an abnormal data judgment operation is performed; if abnormal data exists, a new feature space is established based on the fire equipment to be detected, and a similarity matching operation is performed; if no abnormal data exists, a database addition operation is performed based on the sample data of the fire equipment to be detected.

[0077] Exemplarily, in the case where the test results do not match the corresponding type of fire-fighting equipment, the present invention takes into account a variety of possibilities. First, when it is found that the fire-fighting equipment itself has abnormal data, these abnormal data will be introduced into the original support vector machine model to construct a new feature space, which is composed of the original feature space and the newly added abnormal data, and the new feature space is recalculated and analyzed to more accurately evaluate the performance of the equipment. Secondly, if the test results show that there is no abnormal data for the fire-fighting equipment, or although there is abnormal data but it does not meet specific conditions, the relevant information of the fire-fighting equipment should be added to the database as new sample data to enhance the comprehensiveness and representativeness of the database. This mechanism ensures the flexibility and adaptability of the detection system and effectively improves the ability to identify and manage the status of fire-fighting equipment.

[0078] In the above embodiment, through in-depth analysis of the similarity value, the historical samples closest to the current equipment status can be effectively selected to generate accurate detection results. These detection results can not only comprehensively evaluate the operating status of the equipment and determine whether it is in normal operation, but also timely identify potential faults or make necessary maintenance suggestions. For example, when the operating parameters of a fire-fighting equipment are compared with historical data, if it is found that the similarity with the previous normal operation sample is high, but there is a slight deviation, this may indicate that the equipment is about to face problems. At this time, the management team can take measures in advance, such as arranging maintenance or adjusting operations, so as to reduce the risk of equipment failure. In addition, the results of similarity matching can also help identify the long-term trend of equipment performance and ensure that the fire-fighting equipment maintains an efficient and reliable working state at critical moments. This process not only improves the accuracy of detection, but also provides reliable data support for subsequent decision-making, enabling managers to formulate more scientific maintenance plans, optimize resource allocation, and ultimately enhance the safety and operating efficiency of equipment. This method based on similarity analysis has greatly promoted the intelligent process of equipment management, and effectively improved the accuracy of fire-fighting equipment detection, providing a more solid guarantee for ensuring public safety.

[0079] Exemplarily, the similarity matching operation is performed based on the data similarity to obtain the fire-fighting equipment detection result, including: if rij>s, the fire-fighting equipment to be detected corresponding to the sample data is qualified; if rij≤s, the fire-fighting equipment to be detected corresponding to the sample data is unqualified, wherein s is a preset detection threshold and rij is the data similarity.

[0080] It should also be specifically noted that if the similarity is high, it indicates that the detection result of the fire-fighting equipment to be detected matches the fire-fighting equipment of the corresponding type. If the similarity is low, it indicates that the detection result of the fire-fighting equipment to be detected does not match the fire-fighting equipment of the corresponding type.

[0081] The following describes the working process of the present invention using a common scenario as an example. Figure 1 , Figure 1 The invention is a flow chart of a fire protection equipment detection method.

[0082] Step 1: Collect equipment type and working parameter data of the fire-fighting equipment to be tested;

[0083] Step 2: Extract the collected working parameter data to generate sample data, including known parameter data and test results;

[0084] Step 3: Perform feature mapping operation based on sample data to construct feature space;

[0085] Step 4: Use feature space, working parameter data and sample data to perform kernel skill calculation to obtain data similarity;

[0086] Step 5: Perform similarity matching based on data similarity to obtain the detection results of fire-fighting equipment.

[0087] In summary, the present invention provides a fire equipment detection method, comprising: during the operation of the fire equipment to be detected, obtaining the equipment type and working parameter data collected from the fire equipment to be detected; performing a data extraction operation based on the equipment type and the working parameter data to obtain sample data, wherein the sample data includes known parameter data and a detection result; performing a feature mapping operation based on the sample data to obtain a feature space; performing a kernel technique calculation operation based on the feature space, the working parameter data and the sample data to obtain data similarity; performing a similarity matching operation based on the data similarity to obtain a fire equipment detection result.

[0088] The embodiment of the present invention also provides a fire fighting equipment detection system, such as Figure 2 As shown, it is a structural block diagram of a fire equipment detection system provided by an embodiment of the present invention, including:

[0089] The data acquisition module 1 is used to acquire the equipment type and working parameter data collected from the fire-fighting equipment to be detected during its operation;

[0090] Data extraction module 2, used to perform data extraction operation according to the device type and the working parameter data to obtain sample data, wherein the sample data includes known parameter data and test results;

[0091] A feature space obtaining module 3 is used to perform a feature mapping operation according to the sample data to obtain a feature space;

[0092] A similarity calculation module 4 is used to perform a kernel skill calculation operation according to the feature space, the working parameter data and the sample data to obtain data similarity;

[0093] The similarity matching module 5 is used to perform a similarity matching operation according to the data similarity to obtain a fire-fighting equipment detection result.

[0094] In an optional embodiment, the system is further used for:

[0095] Before performing a feature mapping operation on the sample data to obtain a feature space, the method further includes: performing a preprocessing and analysis operation on the sample data to obtain sample processed data.

[0096] In an optional embodiment, the system is further used for:

[0097] The preprocessing and analysis operations are performed on the sample data to obtain sample processed data, including: performing an abnormal data cleaning operation on the sample data to obtain denoised data, wherein the denoised data includes denoised known parameter data and denoised detection results; performing a principal component analysis operation on the denoised known parameter data to obtain sample processed data.

[0098] In an optional implementation, the feature space obtaining module 3 is further used for:

[0099] The method of performing a feature mapping operation based on the sample data to obtain a feature space includes: performing a feature mapping operation based on the known parameter data after denoising and the detection result after denoising to obtain the feature space, wherein the known parameter data after denoising is used as an input parameter of the feature space, and the detection result after denoising is used as an output parameter of the feature space, the known parameter data after denoising includes the length of the water hose, the cross-sectional radius of the pipe joints at both ends, the cross-sectional area and the wall thickness of the water hose, and the detection result after denoising includes the bursting pressure of the water hose.

[0100] In an optional embodiment, the system is further used for:

[0101] The feature mapping operation is to establish a nonlinear regression model operation using a support vector machine kernel function, including: the formula for establishing a nonlinear regression model operation is:

[0102]

[0103] Among them, K(x i , x j ) is the support vector machine kernel function; x i is the i-th sample data, x j is the jth sample data, ||x i -x j || is x i With x j The Euclidean distance between them, ∈ and σ are the support vector machine kernel function parameters, and the support vector machine kernel function parameters ∈ and α are determined by cross-validation method.

[0104] In an optional implementation, the similarity calculation module 4 is further used for:

[0105] The kernel skill calculation operation is performed according to the feature space, the working parameter data and the sample data to obtain the data similarity, including: the kernel skill calculation operation formula is:

[0106] rij=K(bij,Di)

[0107] Among them, bij is the working parameter data, bi is the sample data, K is the support vector machine kernel function of the feature space, and rij is the data similarity.

[0108] In an optional implementation, the similarity calculation module 4 is further used for:

[0109] The similarity matching operation is performed based on the data similarity to obtain the fire equipment detection result, including: if the denoised detection result matches the fire equipment to be detected, a similarity matching operation is performed; if the denoised detection result does not match the fire equipment to be detected, an abnormal data judgment operation is performed; if abnormal data exists, a new feature space is established based on the fire equipment to be detected, and a similarity matching operation is performed; if no abnormal data exists, a database addition operation is performed based on the sample data of the fire equipment to be detected.

[0110] In an optional implementation, the similarity matching module 5 is further used for:

[0111] The similarity matching operation is performed based on the data similarity to obtain the fire-fighting equipment detection result, including: if rij>s, the fire-fighting equipment to be detected corresponding to the sample data is qualified; if rij≤s, the fire-fighting equipment to be detected corresponding to the sample data is unqualified, wherein s is a preset detection threshold and rij is the data similarity.

[0112] The embodiment of the present invention further provides a device, which includes: a processor, a memory, and a computer program stored in the memory and executable on the processor, wherein the processor implements the fire equipment detection method described in the above embodiment when executing the computer program.

[0113] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the device.

[0114] The device may be a computing device such as a desktop computer, a notebook, a PDA, and a smart tablet. The device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the above components are merely examples of the device and do not constitute a limitation on the device. The device may include more or fewer components than the above, or a combination of certain components, or different components. For example, the device may also include input and output devices, network access devices, buses, etc.

[0115] The processor may be a central processing unit (CPU), other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the device, and various interfaces and lines are used to connect the various parts of the entire device.

[0116] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0117] Wherein, if the module / unit integrated in the device 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, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media do not include electric carrier signals and telecommunication signals.

[0118] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0119] Compared with the prior art, the beneficial effects of the embodiments of the present invention are as follows: in the present invention, by testing the fire-fighting equipment, the following advantages are achieved: the test results are accurate and the test efficiency is high; there is no need to simulate extreme environments multiple times, and sufficient data can be obtained by one test, which greatly saves the test cost; it can be applied to a variety of fire-fighting equipment, and has strong applicability and comprehensiveness; the fire-fighting equipment is automated and batch tested through the measuring equipment, so as to avoid human measurement errors and improve the test efficiency and accuracy; the fire-fighting equipment cost is reduced and the effectiveness of the fire-fighting equipment test is guaranteed; the clamping device for clamping the water hose can be automatically adjusted according to different water hose diameters and lengths, and the operation is convenient and fast. The specific test process is as follows: in the process of the fire-fighting equipment to be tested working, the equipment type and working parameter data collected from the fire-fighting equipment to be tested are obtained. Then, a data extraction operation is performed according to the equipment type and the working parameter data to obtain sample data, and the sample data includes known parameter data and test results. Then, a feature mapping operation is performed on the sample data to obtain a feature space. Then, a kernel skill calculation operation is performed according to the feature space, the working parameter data and the sample data to obtain the similarity between the working parameter data and the sample data. Finally, a similarity matching operation is performed based on the similarity to obtain the fire equipment detection result. According to the above method, the detection of fire equipment is realized, and the whole process does not require manual measurement and data analysis, which avoids human measurement errors, thereby significantly improving the detection accuracy of fire equipment.

[0120] The specific embodiments described above further describe the purpose, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific embodiment of the present invention and is not intended to limit the scope of protection of the present invention. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A fire fighting equipment detection method, It is characterized in that include: During the operation of the fire-fighting equipment to be detected, obtaining equipment type and operating parameter data collected from the fire-fighting equipment to be detected; Performing a data extraction operation according to the device type and the working parameter data to obtain sample data, wherein the sample data includes known parameter data and a test result; Performing a feature mapping operation according to the sample data to obtain a feature space; Performing a kernel skill calculation operation according to the feature space, the working parameter data and the sample data to obtain data similarity; A similarity matching operation is performed based on the data similarity to obtain a fire-fighting equipment detection result.

2. The fire fighting equipment detection method according to claim 1, It is characterized in that Before performing a feature mapping operation according to the sample data to obtain a feature space, the method further includes: Preprocessing and analyzing operations are performed according to the sample data to obtain sample processing data.

3. The fire fighting equipment detection method according to claim 2, It is characterized in that The preprocessing and analyzing operations are performed according to the sample data to obtain sample processing data, including: According to the sample data, an abnormal data cleaning operation is performed to obtain denoised data, wherein the denoised data includes denoised known parameter data and denoised detection results; A principal component analysis operation is performed based on the known parameter data after denoising to obtain sample processing data.

4. The fire fighting equipment detection method according to claim 3, It is characterized in that The step of performing a feature mapping operation according to the sample data to obtain a feature space includes: A feature mapping operation is performed based on the known parameter data after denoising and the detection result after denoising to obtain the feature space, wherein the known parameter data after denoising serves as the input parameter of the feature space, and the detection result after denoising serves as the output parameter of the feature space, the known parameter data after denoising includes the length of the water hose, the cross-sectional radius of the pipe joints at both ends, the cross-sectional area and the wall thickness of the water hose, and the detection result after denoising includes the bursting pressure of the water hose.

5. The fire fighting equipment detection method according to claim 4, It is characterized in that The feature mapping operation is an operation of establishing a nonlinear regression model using a support vector machine kernel function, including: The operating formula for establishing a nonlinear regression model is: Among them, K(x i , x j ) is the support vector machine kernel function; x i is the i-th sample data, x j is the jth sample data, ||x i -x j || is x i With x j The Euclidean distance between them, ∈ and σ are support vector machine kernel function parameters, and the support vector machine kernel function parameters ∈ and σ are determined by cross-validation method.

6. The fire fighting equipment detection method according to claim 5, It is characterized in that The performing a kernel skill calculation operation according to the feature space, the working parameter data and the sample data to obtain data similarity includes: The kernel trick calculation operation formula is: rij=K(bij,bi) Among them, bij is the working parameter data, bi is the sample data, K is the support vector machine kernel function of the feature space, and rij is the data similarity.

7. The fire fighting equipment detection method according to claim 3, It is characterized in that The similarity matching operation is performed according to the data similarity to obtain the fire equipment detection result, including: If the denoised detection result matches the fire-fighting equipment to be detected, a similarity matching operation is performed; If the denoising detection result does not match the fire-fighting equipment to be detected, an abnormal data judgment operation is performed; if abnormal data exists, a new feature space is established based on the fire-fighting equipment to be detected, and a similarity matching operation is performed; if abnormal data does not exist, a database addition operation is performed based on the sample data of the fire-fighting equipment to be detected.

8. The fire fighting equipment detection method according to claim 6, It is characterized in that The similarity matching operation is performed according to the data similarity to obtain the fire equipment detection result, including: If rij>s, the fire-fighting equipment to be detected corresponding to the sample data is qualified; if rij≤s, the fire-fighting equipment to be detected corresponding to the sample data is unqualified, wherein s is the preset detection threshold and rij is the data similarity.

9. A fire equipment detection system, It is characterized in that include: A data acquisition module, used to acquire equipment type and working parameter data collected from the fire-fighting equipment to be detected during its operation; A data extraction module, used to perform a data extraction operation according to the device type and the working parameter data to obtain sample data, wherein the sample data includes known parameter data and a test result; A feature space obtaining module, used for performing a feature mapping operation according to the sample data to obtain a feature space; A similarity calculation module, used to perform a kernel skill calculation operation according to the feature space, the working parameter data and the sample data to obtain data similarity; The similarity matching module is used to perform a similarity matching operation according to the data similarity to obtain a fire-fighting equipment detection result.

10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute the fire-fighting equipment detection method according to any one of claims 1 to 8.

Images