Meteorological instrument fault detection system and method

Abstract

The invention relates to the technical field of meteorological instrument detection, and particularly discloses a meteorological instrument fault detection system and method, and the method comprises the steps: firstly setting a test condition, collecting the response characteristic data of each core part of a tested meteorological instrument under the action of the test condition, and then carrying out the detection of a fault of the tested meteorological instrument; and performing significance analysis and aggregation processing on the response characteristic data of each core component by adopting a deep learning-based data processing technology to capture the overall response characteristic of the core component of the tested meteorological instrument, and further performing fine-grained interaction analysis on the test condition and the overall response characteristic of the core component to obtain the overall response characteristic of the tested meteorological instrument. The correlation mode between the test condition and the response characteristic of the core component is mined, and whether the tested meteorological instrument breaks down or not is intelligently identified based on the correlation mode. Therefore, by simulating different working scenes, the accuracy and timeliness of fault detection of the meteorological instrument can be effectively improved, so that the reliability of meteorological data is ensured.

Description

Technical Field

[0001] The present application relates to the field of meteorological instrument detection technology, and more specifically, to a meteorological instrument fault detection system and method. Background Art

[0002] As key equipment for meteorological observation and prediction, the accuracy and reliability of meteorological instruments are directly related to the accuracy and timeliness of weather forecasts, and have a significant impact on many fields such as agricultural production, transportation, environmental protection, and disaster warning. However, during the long-term operation of meteorological instruments, due to environmental factors (such as extreme weather, temperature changes, humidity fluctuations, etc.), mechanical wear, aging of electronic components and other reasons, it is inevitable that meteorological instruments will fail or perform poorly. If the fault cannot be detected and repaired in time, it may cause distortion of observation data, which in turn affects subsequent meteorological analysis and decision-making.

[0003] Traditional meteorological instrument fault detection methods mainly rely on manual regular inspection and maintenance, including appearance inspection, functional testing, and simple performance parameter comparison. Such methods are not only time-consuming and laborious, but also often fail to capture some hidden or intermittent faults and cannot effectively identify them in the early stages of the occurrence of faults, which may lead to the accumulation of data errors and affect the accuracy and timeliness of weather forecasts.

[0004] Therefore, an optimized meteorological instrument fault detection method and system are desired. Summary of the invention

[0005] The present application provides a meteorological instrument fault detection system and method, which can effectively improve the accuracy and timeliness of meteorological instrument fault detection by simulating different working scenarios, thereby ensuring the reliability of meteorological data.

[0006] In a first aspect, a meteorological instrument fault detection method is provided, comprising: Setting test conditions, wherein the test conditions include an input voltage value, an input current value, and an optical signal strength value; Collecting response characteristic data of each core component of the tested meteorological instrument under the test conditions to obtain a set of core component response characteristic data; Embedding the test condition to obtain a low-dimensional embedded coding vector of the test condition; Performing dynamic feature aggregation based on embedded coding on the set of core component response characteristic data to obtain a core component response characteristic significant aggregation coding vector; Performing feature fine-grained interaction based on external knowledge enhancement on the core component response characteristic significant aggregation coding vector and the test condition low-dimensional embedded coding vector to obtain a test condition-component response characteristic fine-grained interaction coding vector; Based on the test condition-component response characteristic fine-grained interaction encoding vector, it is determined whether the meteorological instrument under test fails.

[0007] In a second aspect, a meteorological instrument fault detection system is provided, comprising: A test condition setting module, used to set test conditions, wherein the test conditions include input voltage value, input current value and optical signal strength value; A response characteristic data acquisition module, used to acquire the response characteristic data of each core component of the tested meteorological instrument under the test conditions to obtain a set of core component response characteristic data; A test condition embedding coding module, used for embedding the test condition to obtain a low-dimensional embedding coding vector of the test condition; A feature dynamic aggregation processing module, used for performing feature dynamic aggregation based on embedded coding on the set of core component response characteristic data to obtain a core component response characteristic significant aggregation coding vector; A feature fine-grained interaction processing module, used for performing feature fine-grained interaction based on external knowledge enhancement on the core component response characteristic significant aggregation coding vector and the test condition low-dimensional embedded coding vector to obtain a test condition-component response characteristic fine-grained interaction coding vector; The meteorological instrument test result determination module is used to determine whether the meteorological instrument under test fails based on the test condition-component response characteristic fine-grained interactive coding vector.

[0008] The present application provides a meteorological instrument fault detection system and method, which first sets test conditions, collects response characteristic data of each core component of the tested meteorological instrument under the effect of the test conditions, and then uses data processing technology based on deep learning to perform significance analysis and aggregation processing on the response characteristic data of each core component to capture the overall response characteristics of the core components of the tested meteorological instrument, and then, through fine-grained interactive analysis of the test conditions and the overall response characteristics of the core components, to dig out the correlation pattern between the test conditions and the response characteristics of the core components, based on which to intelligently identify whether the tested meteorological instrument has a fault. In this way, by simulating different working scenarios, the accuracy and timeliness of meteorological instrument fault detection can be effectively improved, thereby ensuring the reliability of meteorological data. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings of the embodiments of the present application are briefly introduced below. Obviously, the drawings described below only relate to some embodiments of the present application, and are not intended to limit the present application.

[0010] Figure 1A schematic flowchart of a meteorological instrument fault detection method according to an embodiment of the present application.

[0011] Figure 2 A data flow diagram of a meteorological instrument fault detection method according to an embodiment of the present application.

[0012] Figure 3 This is a schematic flow chart of step S4 in the meteorological instrument fault detection method according to an embodiment of the present application.

[0013] Figure 4 This is a schematic flow chart of step S5 in the meteorological instrument fault detection method according to an embodiment of the present application.

[0014] Figure 5 This is a schematic block diagram of a meteorological instrument fault detection system according to an embodiment of the present application. DETAILED DESCRIPTION

[0015] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work also fall within the scope of protection of the present application.

[0016] In view of the above technical problems, the technical concept of the present application is as follows: first, the test conditions are set, and the response characteristic data of each core component of the tested meteorological instrument under the effect of the test conditions are collected. Then, the response characteristic data of each core component is analyzed and aggregated by using data processing technology based on deep learning to capture the overall response characteristics of the core components of the tested meteorological instrument. Then, the correlation pattern between the test conditions and the overall response characteristics of the core components is mined by conducting fine-grained interactive analysis of the test conditions and the response characteristics of the core components, so as to intelligently identify whether the tested meteorological instrument has failed. In this way, by simulating different working scenarios, the accuracy and timeliness of meteorological instrument fault detection can be effectively improved, thereby ensuring the reliability of meteorological data.

[0017] like Figure 1 and Figure 2As shown, the meteorological instrument fault detection method includes: S1, setting test conditions, wherein the test conditions include input voltage value, input current value and optical signal strength value; S2, collecting response characteristic data of each core component of the tested meteorological instrument under the action of the test conditions to obtain a set of core component response characteristic data; S3, embedding and coding the test conditions to obtain a low-dimensional embedded coding vector of the test conditions; S4, dynamically aggregating the features of the set of core component response characteristic data based on embedded coding to obtain a core component response characteristic significantly aggregated coding vector; S5, performing feature fine-grained interaction based on external knowledge enhancement on the core component response characteristic significantly aggregated coding vector and the test condition low-dimensional embedded coding vector to obtain a test condition-component response characteristic fine-grained interaction coding vector; S6, determining whether the tested meteorological instrument has a fault based on the test condition-component response characteristic fine-grained interaction coding vector.

[0018] Exemplarily, in step S1, test conditions are set, and the test conditions include input voltage value, input current value and optical signal strength value. It should be understood that the input voltage and current values ​​directly affect the working efficiency and stability of electronic components, while the optical signal strength has an important impact on the components in the meteorological instrument that rely on optical sensing. By setting the test conditions, the actual working scene of the meteorological instrument can be simulated to obtain comprehensive information about each core component of the device under test, which helps to discover potential problems or early signs of failure.

[0019] Exemplarily, in step S2, the response characteristic data of each core component of the tested meteorological instrument under the test conditions are collected to obtain a collection of core component response characteristic data. It should be understood that each core component in the meteorological instrument may have different response characteristics to input conditions (such as voltage, current, light signal intensity). Therefore, by collecting the response characteristic data of all core components, it is possible to fully understand the performance of each component under specific test conditions, obtain a comprehensive view of the overall health status of the tested meteorological instrument, and provide a comprehensive data basis for subsequent fault detection and analysis. In an embodiment of the present application, the response characteristic data includes but is not limited to voltage, current, power, component surface temperature, light intensity, etc.

[0020] Exemplarily, in step S3, the test condition is embedded and coded to obtain a low-dimensional embedded coding vector of the test condition. It should be understood that, considering that the response characteristic data of the core component is a comprehensive reflection of the meteorological instrument under the combined action of the input voltage value, the input current value and the light signal intensity value, in order to capture the inherent connection between the multidimensional information in the test condition, the present application further embeds and codes the test condition to compress the multidimensional information of the test condition into a unified low-dimensional feature space, so as to identify and express the potential correlation between the multidimensional information, and realize the combined analysis of the multidimensional test condition. In an embodiment of the present application, a fully connected neural network model is used to train and generate a test condition embedding coding matrix, so as to embed and code the test condition to obtain a low-dimensional embedded coding vector of the test condition.

[0021] Exemplarily, in step S4, the set of the core component response characteristic data is subjected to feature dynamic aggregation based on embedded coding to obtain a core component response characteristic significant aggregation coding vector. It should be understood that, considering that there are many core components of meteorological instruments, and there is a certain nonlinear correlation between the response characteristic data of each core component, therefore, in order to capture the interaction and correlation influence between each core component, and then to mine the significant response pattern of the core components of the meteorological instrument as a whole, the present application further performs feature dynamic analysis and significant aggregation processing on the set of the core component response characteristic data to reveal the overall response characteristics of the core components of the meteorological instrument.

[0022] In one embodiment, Figure 3 As shown, the set of core component response characteristic data is dynamically aggregated based on embedded coding features to obtain a core component response characteristic significantly aggregated coding vector, including: S41, each core component response characteristic data in the set of core component response characteristic data is passed through an embedding layer to obtain a set of core component response characteristic semantic embedded coding vectors; S42, based on the characteristic static potential energy distribution of the set of core component response characteristic semantic embedded coding vectors, a core component response characteristic pseudo-anchored aggregation center representation vector is calculated; S43, the aggregation movement direction of each core component response characteristic semantic embedded coding vector in the set of core component response characteristic semantic embedded coding vectors relative to the core component response characteristic pseudo-anchored aggregation center representation vector is calculated to obtain a set of core component response characteristic aggregation movement directions; S44, based on the set of core component response characteristic aggregation movement directions, the set of core component response characteristic semantic embedded coding vectors is dynamically aggregated toward the core component response characteristic pseudo-anchored aggregation center representation vector to obtain the core component response characteristic significantly aggregated coding vector.

[0023] Exemplarily, in step S41, each core component response characteristic data in the set of core component response characteristic data is respectively passed through an embedding layer to obtain a set of core component response characteristic semantic embedding coding vectors. It should be understood that the response characteristic data of each core component is respectively embedded and encoded through an embedded coding technology to map it to a unified feature space, obtain a semantic embedding representation of each core component response characteristic data, and thus obtain a set of core component response characteristic semantic embedding coding vectors.

[0024] In one embodiment, in step S42, based on the characteristic static potential energy distribution of the set of the core component response characteristic semantic embedding coding vectors, the core component response characteristic pseudo-anchor aggregation center representation vector is calculated, including: inputting each core component response characteristic semantic embedding coding vector in the set of the core component response characteristic semantic embedding coding vector into the characteristic static potential energy measurement network to obtain a set of core component response characteristic static potential energy measurement coefficients; inputting the set of core component response characteristic static potential energy measurement coefficients into the characteristic energy level screening gating unit to obtain a set of core component response characteristic static potential energy weight factors; based on the set of core component response characteristic static potential energy weight factors, calculating the weighted sum of the set of core component response characteristic semantic embedding coding vectors to obtain the core component response characteristic pseudo-anchor aggregation center representation vector. Specifically, the process can be expressed by the formula:

[0025]

[0026]

[0027]

[0028]

[0029] in, represents a set of semantic embedding coding vectors of the response characteristics of the core components, , , and Respectively represent the first, second, and third in the set of the core component response characteristic semantic embedding coding vectors and The core components respond to the characteristic semantic embedding encoding vector, is the number of feature vectors in the set of semantic embedding encoding vectors of the core component response characteristics, Indicates the The core component response feature semantic embedding encoding vector The eigenvalues ​​at the positions, and Respectively represent the The feature mean and feature variance of the semantic embedding encoding vector of the core component response characteristics, is the characteristic scale value of the semantic embedding encoding vector of the core component response characteristic, For the said The static potential energy metric coefficient of the semantic embedding encoding vector of the core component response characteristics, Indicates Normalized core component response characteristic static potential energy measurement coefficient, represents the gated mask function, represents the gating threshold, Indicates The static potential energy weight factor of the core component response characteristics, The pseudo-anchored aggregation center representation vector represents the core component response characteristics.

[0030] That is, by measuring the feature potential energy of the semantic embedded coding vectors of the response characteristics of each core component, the potential energy level of the response characteristic data of each core component under static conditions, as well as the importance and influence of the global core component responsiveness characteristic distribution, are revealed, thereby obtaining a set of static potential energy measurement coefficients of the core component response characteristics. Then, through the gating mechanism, the obtained set of static potential energy measurement coefficients of the core component response characteristics is subjected to gated masking processing to screen out individual features that contribute more to the overall response characteristics of the core components of the meteorological instrument, and assign corresponding weight factors to them, while suppressing individual features that contribute less to reduce the impact of noise and irrelevant information on the final fault detection. Furthermore, based on the obtained weight factors, the set of semantic embedded coding vectors of the response characteristics of the core components is weightedly aggregated to reveal the trend center of the response characteristics of each core component, and generate a pseudo-anchored aggregation center representation vector of the response characteristics of the core components, so as to reflect the essential response characteristics of the core components of the meteorological instrument, thereby providing effective guidance for the subsequent aggregation process of the response characteristics of individual components.

[0031] Specifically, the feature static potential energy measurement network is first used to evaluate the stability or "potential energy" of the semantic embedding encoding vector of the response characteristics of each core component under the current test conditions. This step can help identify which components' behavior patterns are stable and which are unstable under given conditions. Next, the gating units are screened by feature energy levels, and the weights of each response characteristic are further filtered and adjusted according to the measurement results. The role of the gating unit is to strengthen the core component features that have a greater impact on the overall response characteristics of the meteorological instrument, while weakening or ignoring those features that contribute less to the global behavior or may be outliers. Such processing helps to remove irrelevant information, so that subsequent analysis can focus more on meaningful data. Finally, a pseudo-anchored aggregation center representation vector is determined based on the calculated set of static potential energy weight factors of the core component response characteristics. This aggregation center actually reflects the average response trend of all tested core components under specific test conditions, and it is used as a reference point to measure the position of other individual components relative to the overall performance. In this way, the comprehensive response characteristics of the entire meteorological instrument in different working scenarios can be captured more accurately, providing a solid foundation for the subsequent fine-grained interaction analysis. This approach also increases the system's sensitivity to potential failures because it highlights important changes that may indicate an impending problem, even if those changes do not seem significant at first.

[0032] That is, each core component response characteristic semantic embedding coding vector in the set of core component response characteristic semantic embedding coding vectors is respectively input into the characteristic static potential energy measurement network to obtain a set of core component response characteristic static potential energy measurement coefficients, including: performing Z-score normalization processing on the core component response characteristic semantic embedding coding vector to obtain a standardized core component response characteristic semantic embedding coding vector; calculating the sum of the cube of each eigenvalue in the standardized core component response characteristic semantic embedding coding vector and dividing it by the characteristic scale value of the standardized core component response characteristic semantic embedding coding vector to obtain the core component response characteristic static potential energy measurement coefficient.

[0033] Exemplarily, in step S43, the aggregate motion direction of each core component response characteristic semantic embedding coding vector in the set of the core component response characteristic semantic embedding coding vector is calculated relative to the core component response characteristic pseudo-anchor aggregation center representation vector to obtain a set of core component response characteristic aggregate motion directions. In one embodiment, the core component response characteristic aggregate motion direction is the arc cosine function value between the core component response characteristic semantic embedding coding vector and the core component response characteristic pseudo-anchor aggregation center representation vector. Specifically, the process can be expressed by the formula:

[0034] in, The first one in the set of semantic embedding encoding vectors representing the response characteristics of the core component The core components respond to the characteristic semantic embedding encoding vector, The pseudo-anchor aggregation center representation vector represents the core component response characteristics, represents the magnitude of a vector, is the arccosine function, Indicates the The semantic embedding encoding vectors of the core component response characteristics represent the aggregate movement direction of the pseudo-anchored aggregation center representation vector of the core component response characteristics.

[0035] Specifically, when the response characteristics of all core components are converted into low-dimensional semantic embedding encoding vectors, these vectors together constitute a spatial distribution that reflects the overall health status of the equipment. By determining a pseudo-anchored aggregation center representation vector, that is, an average or typical state of the response characteristics of all core components, it can be used as a reference point to evaluate whether the behavior of individual components deviates from expectations. Then, for each core component response characteristic semantic embedding encoding vector, the angular difference between it and the pseudo-anchored aggregation center is calculated, and the inverse cosine function is usually used to measure the angle between the two vectors. This angular difference actually represents the "movement direction" of the core component relative to the overall response characteristics, revealing its dynamic role in the global response pattern. This aggregated movement direction not only describes how individual components change with test conditions, but also shows their mutual relationship and synergy in the entire meteorological instrument. For example, in normal operation, most core components may show similar movement directions, indicating that they respond to environmental changes in a coordinated manner; while in the case of failure, some abnormal components may show significantly different movement directions, suggesting that their behavior has deviated from the normal group pattern. Therefore, by analyzing these aggregate motion directions, potential problems or early signs of failure can be identified earlier, even if these problems have not yet caused noticeable performance degradation.

[0036] That is, by calculating the aggregation movement direction of the semantic embedding coding vector of each core component response characteristic relative to the pseudo-anchor aggregation center representation vector of the core component response characteristic, the change trend of each individual feature relative to the center point is quantified, revealing the dynamic relationship of each individual feature within the core component response characteristic space and its evolution path, so as to identify the relative relationship between features and group behavior patterns.

[0037] Exemplarily, in step S44, based on the set of the core component response characteristic aggregation movement directions, the set of the core component response characteristic semantic embedding coding vectors is dynamically aggregated toward the core component response characteristic pseudo-anchor aggregation center representation vector to obtain the core component response characteristic significant aggregation coding vector. Specifically, the process can be expressed as:

[0038] in, The first one in the set of semantic embedding encoding vectors representing the response characteristics of the core component The core components respond to the characteristic semantic embedding encoding vector, For the said The static potential energy metric coefficient of the semantic embedding encoding vector of the core component response characteristics, The pseudo-anchor aggregation center representation vector represents the core component response characteristics, Indicates the The aggregate movement direction of the semantic embedding encoding vector of the core component response characteristics relative to the pseudo-anchor aggregation center representation vector of the core component response characteristics, represents the sine function, and denote the weight matrix and bias term respectively, A coding vector representing a significant aggregation of the core component response characteristics.

[0039] It should be understood that by calculating the aggregated motion direction of the semantic embedding coding vector of the response characteristics of each core component relative to the pseudo-anchored aggregation center, the present application has obtained an understanding of how each component changes relative to the global behavior under specific test conditions. Next, using these aggregated motion direction information, the semantic embedding coding vectors of the response characteristics of each core component can be guided to dynamically adjust toward the pseudo-anchored aggregation center. This adjustment is not a simple averaging process, but a weighted aggregation based on the specific motion direction of each component and its importance in the overall response. Doing so can ensure that the component features that contribute more to the overall response characteristics are fully emphasized, while relatively less important or possibly noisy data are appropriately suppressed. During the dynamic aggregation process, the semantic embedding coding vectors of the response characteristics of the core components will gradually approach the pseudo-anchored aggregation center representation vector, but at the same time retain their own unique "motion trajectory". This means that the final significant aggregation coding vector not only represents a static average state, but also integrates the dynamic response characteristics of all core components under different conditions. Such a coding vector can more accurately reflect the overall health status of meteorological instruments and their performance trends in various working scenarios.

[0040] That is, based on the aggregation movement direction and characteristic static potential energy measurement coefficient of the semantic embedding coding vector of the response characteristics of each core component, the semantic embedding coding vector of the response characteristics of each core component is dynamically aggregated toward the pseudo-anchored aggregation center representation vector of the core component response characteristics, so as to realize the dynamic characterization of the overall response characteristics of the core components of the meteorological instrument and obtain the significantly aggregated coding vector of the core component response characteristics.

[0041] Exemplarily, in step S5, the core component response characteristic significant aggregation coding vector and the test condition low-dimensional embedded coding vector are subjected to feature fine-grained interaction based on external knowledge enhancement to obtain a test condition-component response characteristic fine-grained interaction coding vector. It should be understood that, considering that the meteorological instrument is in normal working condition, its core components will exhibit specific response patterns for specific test conditions, and when the core components fail, this response pattern will change. Therefore, the present application further interactively analyzes the core component response characteristic significant aggregation coding vector and the test condition low-dimensional embedded coding vector to reveal the association pattern between the meteorological instrument core component response data and the current test conditions, thereby realizing the detection of potential faults.

[0042] In one embodiment, Figure 4 As shown, the core component response characteristic significant aggregation coding vector and the test condition low-dimensional embedded coding vector are subjected to feature fine-grained interaction based on external knowledge enhancement to obtain the test condition-component response characteristic fine-grained interaction coding vector, including: S51, based on external knowledge, the core component response characteristic significant aggregation coding vector and the test condition low-dimensional embedded coding vector are subjected to feature interaction optimization based on the attention mechanism to obtain the external knowledge optimized test condition-component response characteristic fine-grained interaction feature matrix; S52, based on the external knowledge optimized test condition-component response characteristic fine-grained interaction feature matrix, the core component response characteristic significant aggregation coding vector and the test condition low-dimensional embedded coding vector are subjected to feature modulation optimization respectively to obtain the optimized core component response characteristic significant aggregation coding vector and the optimized test condition low-dimensional embedded coding vector; S53, the position point division between the optimized core component response characteristic significant aggregation coding vector and the optimized test condition low-dimensional embedded coding vector is calculated to obtain the test condition-component response characteristic fine-grained interaction coding vector.

[0043] In one embodiment, in step S51, based on external knowledge, the core component response characteristic significant aggregation coding vector and the test condition low-dimensional embedded coding vector are optimized for feature interaction based on the attention mechanism to obtain an external knowledge optimized test condition-component response characteristic fine-grained interaction feature matrix, including: inputting the core component response characteristic significant aggregation coding vector and the test condition low-dimensional embedded coding vector into a fine-grained feature interaction network to obtain a test condition-component response characteristic fine-grained interaction feature matrix; inputting the test condition-component response characteristic fine-grained interaction feature matrix into an attention unit based on external knowledge to obtain the external knowledge optimized test condition-component response characteristic fine-grained interaction feature matrix. Specifically, the process can be expressed as:

[0044]

[0045] in, represents the core component response characteristic significant aggregation encoding vector, represents the low-dimensional embedding coding vector of the test condition, represents the transpose of a vector, represents the matrix multiplication operation, represents the fine-grained interaction feature matrix of test condition-component response characteristics, and represents the learnable memory parameter matrix of the external knowledge-based attention unit, represents the normalization function, Represents the fine-grained interaction feature matrix of test condition-component response characteristics optimized by external knowledge.

[0046] That is, by performing fine-grained feature interaction on the significant aggregation coding vector of the core component response characteristics and the low-dimensional embedded coding vector of the test conditions, the semantic association between the two is understood, and a fine-grained interactive feature matrix of the test condition-component response characteristics is generated. Subsequently, the generated fine-grained interactive feature matrix of the test condition-component response characteristics is sent to the attention unit based on external knowledge to further optimize the fine-grained interactive feature matrix of the test condition-component response characteristics by using external knowledge, thereby enhancing the model's ability to understand the working mode of the meteorological instrument. In a specific implementation, the parameter matrix of the attention unit is trained using external knowledge such as the design principle, working principle, and operating environment information of the meteorological instrument, and the attention unit is guided to perform weighted optimization on the fine-grained interactive feature matrix of the test condition-component response characteristics, so that it can identify and strengthen the important response mode of the meteorological instrument under the current test conditions, thereby capturing the potential connection between the test conditions and the core component response data in a larger range.

[0047] In one embodiment, in step S52, based on the external knowledge optimization test condition-component response characteristic fine-grained interaction feature matrix, the core component response characteristic significant aggregation coding vector and the test condition low-dimensional embedded coding vector are respectively feature modulated and optimized to obtain an optimized core component response characteristic significant aggregation coding vector and an optimized test condition low-dimensional embedded coding vector, including: linearly transforming the core component response characteristic significant aggregation coding vector to obtain a first query feature vector and a first value feature vector and using the external knowledge optimization test condition-component response characteristic fine-grained interaction feature matrix as a key matrix, inputting the first query feature vector, the first value feature vector and the key matrix into a fine-grained modulation module based on a Transformer structure to obtain the optimized core component response characteristic significant aggregation coding vector; linearly transforming the test condition low-dimensional embedded coding vector to obtain a second query feature vector and a second value feature vector and using the external knowledge optimization test condition-component response characteristic fine-grained interaction feature matrix as a key matrix, inputting the second query feature vector, the second value feature vector and the key matrix into the fine-grained modulation module based on a Transformer structure to obtain the optimized test condition low-dimensional embedded coding vector. Specifically, the process can be expressed as:

[0048] in, and denote the first query embedding matrix and the first value embedding matrix respectively, and denote the first query feature vector and the first value feature vector respectively, and denote the second query embedding matrix and the second value embedding matrix respectively, and denote the second query feature vector and the second value feature vector respectively, , , and Represent different bias terms, represents the normalized exponential function, represents the characteristic scale value of the external knowledge optimized fine-grained feature interaction matrix, and They respectively represent the optimized core component response characteristic significant aggregation coding vector and the optimized test condition low-dimensional embedding coding vector.

[0049] Specifically, by performing a linear transformation on the core component response characteristic significantly aggregated coding vector to obtain a first query feature vector and a first value feature vector, and using the test condition-component response characteristic fine-grained interaction feature matrix optimized by external knowledge as a key matrix, a deeper mining of the interactions between the core components can be achieved. This key matrix contains key information learned from a large amount of historical data, which reflects how the various components work together or change independently under different test conditions. When the present application inputs the first query feature vector, the first value feature vector and the key matrix together into a fine-grained modulation module based on a Transformer structure, the module can weight the aggregation of relevant information according to the similarity between the query vector (i.e., the current state of the core component) and the elements in the key matrix, thereby generating a more accurate and representative optimized core component response characteristic significantly aggregated coding vector. This step enhances the model's ability to capture complex relationships between core components, so that abnormal behavior can be accurately identified even in the face of nonlinear or multivariate interaction effects.

[0050] Similarly, the low-dimensional embedded coding vector of the test condition is processed similarly: the second query eigenvector and the second value eigenvector are obtained by linear transformation, and the same key matrix is ​​used again for fine-grained modulation. The goal here is to optimize the test condition representation so that it better reflects the overall response characteristics of the meteorological instrument under specific conditions. In this way, not only can the factors that are critical to the given test conditions be strengthened, but also irrelevant information can be suppressed and noise interference can be reduced. The final optimized low-dimensional embedded coding vector of the test condition provides a purer and more insightful data basis for subsequent analysis.

[0051] Throughout the process, the Transformer-based fine-grained modulation module plays a key role. This architecture is good at handling long sequence dependency problems and can effectively model complex contextual relationships. By introducing the self-attention mechanism, it can flexibly adjust the importance of features at different positions to ensure that each core component or test condition is fully considered from a global perspective. In addition, the use of the fine-grained interaction feature matrix of test condition-component response characteristics optimized by external knowledge as a guide further improves the learning efficiency and generalization ability of the model.

[0052] That is, the fine-grained interaction feature matrix of test conditions and component response characteristics optimized by external knowledge is used as the key matrix, and the first query feature vector and the first value feature vector are constructed based on the significant aggregation coding vector of the core component response characteristics, and the second query feature vector and the second value feature vector are constructed based on the low-dimensional embedding coding vector of the test conditions. The self-attention mechanism of the Transformer structure is used to realize the information exchange and integration between the internal and external knowledge of the features, thereby ensuring that the significant aggregation coding vector of the core component response characteristics and the low-dimensional embedding coding vector of the test conditions can benefit from external knowledge to improve the quality of their feature expression.

[0053] Exemplarily, in step S53, the point-by-point division between the optimized core component response characteristic significant aggregation coding vector and the optimized test condition low-dimensional embedding coding vector is calculated to obtain the test condition-component response characteristic fine-grained interaction coding vector.

[0054]

[0055] in, and They represent the optimized core component response characteristic significant aggregation coding vector and the optimized test condition low-dimensional embedding coding vector respectively. A fine-grained interaction encoding vector representing the test condition-component response characteristic.

[0056] Specifically, when a core component exhibits an abnormality under given test conditions, its corresponding optimized response characteristic encoding vector may show large fluctuations or deviations from the normal range in some dimensions. By dividing by position, the present application can identify the specific locations of these abnormal changes and evaluate their relative importance under the entire test conditions. For example, if the reading of a sensor suddenly increases at a specific voltage level and remains stable under other conditions, the result after the dot division operation will highlight this and help the present application quickly lock in the problem. In addition, this method also helps to eliminate interference between feature values ​​of different scales. Since the raw data may come from a variety of different types and magnitudes of measurements (such as voltage, current, temperature, etc.), direct comparison may cause some high-level features to mask low-level but equally important information. Through the dot division operation, the present application shifts the focus to the relative changes between the features, so that even very subtle differences can be clearly displayed. This is particularly important for discovering small deviations that are not easy to detect but indicate potential failures. The resulting test condition-component response characteristic fine-grained interaction encoding vector combines the information of the optimized core component response characteristics and the test conditions to form a comprehensive representation that reflects the interaction between the two. Such an encoding vector not only contains knowledge about the overall performance of the meteorological instrument under the current working state, but also retains the unique response characteristics of individual components, providing rich contextual information for subsequent analysis. It can help the model more accurately identify which combination patterns are normal and which may be signs of failure, thereby supporting earlier and more reliable fault warnings.

[0057] That is, by performing position-by-position interactive response encoding on the optimized core component response characteristic significant aggregation coding vector and the optimized test condition low-dimensional embedded coding vector in a positional manner, a fine-grained interactive coding vector of test condition-component response characteristics is obtained, thereby comprehensively reflecting the performance of the meteorological instrument under the current test conditions, capturing the correlation pattern between the response data of the core components of the meteorological instrument and the current test conditions, and providing a more intelligent and accurate judgment basis for subsequent fault detection.

[0058] Exemplarily, in step S6, based on the test condition-component response characteristic fine-grained interactive coding vector, it is determined whether the tested meteorological instrument fails. In one embodiment, based on the test condition-component response characteristic fine-grained interactive coding vector, it is determined whether the tested meteorological instrument fails, including: inputting the test condition-component response characteristic fine-grained interactive coding vector into a fault detection module based on a classifier to obtain a fault detection result, and the fault detection result is used to indicate whether the tested meteorological instrument fails. It should be understood that the test condition-component response characteristic fine-grained interactive coding vector already contains rich information about the response characteristics of the core components of the meteorological instrument under different working conditions. However, although this information is detailed, it is still not intuitive or clear enough to be directly used to judge the status of the equipment. Therefore, the purpose of introducing a classifier is to analyze these coding vectors through a machine learning algorithm, thereby realizing the conversion from complex data to simple binary decisions (normal / fault). The classifier can automatically process a large number of complex coding vectors and output a clear result according to predefined standards-that is, whether the meteorological instrument is in a fault state. This not only greatly reduces the need for manual intervention and improves detection efficiency, but also through training, the classifier can learn to identify which combination patterns are usually associated with normal operation and which ones indicate potential problems. This pattern recognition capability enables it to detect abnormalities at an early stage, even if these abnormalities have not yet caused obvious performance degradation. Further, in a specific embodiment, the classifier-based fault detection module uses a Random Forest algorithm.

[0059] Here, in the case where the core component response characteristic significant aggregation coding vector and the test condition low-dimensional embedded coding vector respectively represent the semantic aggregation coding features of the response characteristic data of the core component under predetermined test conditions and the low-dimensional embedded coding features of the predicted test conditions, when performing fine-grained feature interaction based on external knowledge modulation, it is considered that the feature order hierarchy of the core component response characteristic significant aggregation coding vector and the test condition low-dimensional embedded coding vector will cause semantic space mismatch when external knowledge acts on the core component response characteristic significant aggregation coding vector and the test condition low-dimensional embedded coding vector respectively, resulting in the test condition-component response characteristic fine-grained interaction coding vector having a fusion distribution space structure difference, affecting the classification regression convergence consistency, and thus affecting the accuracy of the fault detection result obtained by the fault detection module based on the classifier.

[0060] Preferably, passing the test condition-component response characteristic fine-grained interaction encoding vector through a classifier-based fault detection module to obtain a fault detection result comprises: Determine the eigenvalue mean corresponding to the fine-grained interaction encoding vector of the test condition-component response characteristic , and perform dot addition of the test condition-component response characteristic fine-grained interaction encoding vector and the eigenvalue mean, and then perform dot multiplication of the dot addition result and the eigenvalue mean to obtain the test condition-component response characteristic fine-grained interaction position ambiguity interaction vector ,in, represents the test condition-component response characteristic fine-grained interaction encoding vector, represents the mean of the eigenvalues ​​corresponding to the fine-grained interaction encoding vector of the test condition-component response characteristic, that is, the mean of all eigenvalues ​​of the calculation vector, Indicates point addition, represents dot product; Determine the standard deviation of the eigenvalues ​​corresponding to the fine-grained interaction encoding vector of the test condition-component response characteristic , and further perform point-wise subtraction of the test condition-component response characteristic fine-grained interactive position ambiguity interaction vector and the eigenvalue standard deviation vector from the test condition-component response characteristic fine-grained interactive encoding vector to obtain the test condition-component response characteristic fine-grained interactive position equilibrium metric vector ,in, represents the standard deviation of the eigenvalues ​​corresponding to the fine-grained interaction encoding vector of the test condition-component response characteristic, that is, the standard deviation of all eigenvalues ​​of the calculation vector, Indicates point addition, Indicates point reduction; The bit-by-bit inverse of the test condition-component response characteristic fine-grained interaction position equalization metric vector After adding the test condition-component response characteristic fine-grained interaction position ambiguity interaction vector, the test condition-component response characteristic fine-grained interaction encoding vector is multiplied to obtain the test condition-component response characteristic fine-grained interaction position inference bias vector ; The eigenvalue mean The standard deviation of the eigenvalue The sum is multiplied by the scaling weight hyperparameter After that, it is dot-multiplied with the test condition-component response characteristic fine-grained interactive position inference bias vector to obtain the optimized test condition-component response characteristic fine-grained interactive encoding vector .

[0061] Based on this, in view of the possible spatial structure loss in the high-dimensional space of the feature set of the test condition-component response characteristic fine-grained interaction coding vector, which leads to the convergence inconsistency of the image semantic classification regression based on the implicit inference of spatial structure information, the global feature category of the test condition-component response characteristic fine-grained interaction coding vector is utilized and described with reference to its position structure to construct a distant feature association, thereby establishing the feature proximity association of the test condition-component response characteristic fine-grained interaction coding vector. Furthermore, by estimating the unreduced feature value points of the test condition-component response characteristic fine-grained interaction coding vector, the positional ambiguity information of the object feature value is captured, thereby enhancing the positional inference bias cognitive ability of the feature cluster of the test condition-component response characteristic fine-grained interaction coding vector. In this way, the convergence consistency of classification regression is improved, and the accuracy of the fault detection result obtained by the test condition-component response characteristic fine-grained interaction coding vector through the classifier-based fault detection module is improved.

[0062] In summary, the meteorological instrument fault detection method according to the embodiment of the present application is explained, which first sets the test conditions, collects the response characteristic data of each core component of the tested meteorological instrument under the effect of the test conditions, and then uses the data processing technology based on deep learning to perform significance analysis and aggregation processing on the response characteristic data of each core component to capture the overall response characteristics of the core components of the tested meteorological instrument, and then, through the fine-grained interactive analysis of the test conditions and the overall response characteristics of the core components, to dig out the correlation pattern between the test conditions and the response characteristics of the core components, based on which to intelligently identify whether the tested meteorological instrument has a fault. In this way, by simulating different working scenarios, the accuracy and timeliness of meteorological instrument fault detection can be effectively improved, thereby ensuring the reliability of meteorological data.

[0063] Figure 5 Schematic block diagram of a meteorological instrument fault detection system according to an embodiment of the present application. Figure 5As shown, the meteorological instrument fault detection system 100 includes: a test condition setting module 110, which is used to set the test conditions, and the test conditions include input voltage value, input current value and optical signal strength value; a response characteristic data acquisition module 120, which is used to collect the response characteristic data of each core component of the tested meteorological instrument under the action of the test conditions to obtain a set of core component response characteristic data; a test condition embedded coding module 130, which is used to embed the test conditions to obtain a test condition low-dimensional embedded coding vector; a feature dynamic aggregation processing module 140, which is used to perform feature dynamic aggregation based on embedded coding on the set of core component response characteristic data to obtain a core component response characteristic significant aggregation coding vector; a feature fine-grained interaction processing module 150, which is used to perform feature fine-grained interaction based on external knowledge enhancement on the core component response characteristic significant aggregation coding vector and the test condition low-dimensional embedded coding vector to obtain a test condition-component response characteristic fine-grained interaction coding vector; a meteorological instrument test result determination module 160, which is used to determine whether the tested meteorological instrument has a fault based on the test condition-component response characteristic fine-grained interaction coding vector.

[0064] Here, those skilled in the art will appreciate that the specific operations of the various modules and units in the above-mentioned meteorological instrument fault detection system have been described in detail above. Figures 1 to 4 The meteorological instrument fault detection method has been described in detail, and therefore, its repeated description will be omitted.

[0065] An embodiment of the present application further provides a computer program product, which includes a computer program code. When the computer program code runs on a computer, the computer implements the methods in the above embodiments of the present application.

[0066] An embodiment of the present application further provides a computer-readable storage medium, which stores computer instructions. When the computer instructions are executed on a computer, the computer implements the methods in the above embodiments of the present application.

[0067] An embodiment of the present application also provides a chip, including a circuit, for executing the methods in the above embodiments of the present application.

[0068] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0069] In the description of the embodiments of the present application, unless otherwise specified, " / " means or, for example, A / B can mean A or B; "and / or" in this article is a kind of association relationship that describes associated objects, indicating that three relationships can exist, for example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone. In this application, "at least one" means one or more, and "multiple" means two or more. "At least one of the following items" or similar expressions refers to any combination of these items, including any combination of single items or plural items. For example, at least one of a, b, or c can mean: a, b, c, ab, ac, bc, or abc, where a, b, c can be single or multiple.

[0070] The prefixes such as "first" and "second" used in the embodiments of the present application are only used to distinguish different description objects, and have no limiting effect on the position, order, priority, quantity or content of the described objects. The use of prefixes such as ordinal numbers used to distinguish description objects in the embodiments of the present application does not constitute a limitation on the described objects. For the statement of the described objects, please refer to the description in the context of the claims or embodiments, and the use of such prefixes should not constitute an unnecessary limitation.

[0071] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0072] In the various embodiments of the present application, unless otherwise specified or logically conflicting, the terms and / or descriptions between the various embodiments are consistent and can be referenced to each other, and the technical features in different embodiments can be combined to form new embodiments according to their inherent logical relationships.

[0073] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0074] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0075] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. A meteorological instrument fault detection method, characterized in that: include: Setting test conditions, wherein the test conditions include an input voltage value, an input current value, and an optical signal strength value; Collecting response characteristic data of each core component of the tested meteorological instrument under the test conditions to obtain a set of core component response characteristic data; Embedding the test condition to obtain a low-dimensional embedded coding vector of the test condition; Performing dynamic feature aggregation based on embedded coding on the set of core component response characteristic data to obtain a core component response characteristic significant aggregation coding vector; Performing feature fine-grained interaction based on external knowledge enhancement on the core component response characteristic significant aggregation coding vector and the test condition low-dimensional embedded coding vector to obtain a test condition-component response characteristic fine-grained interaction coding vector; Based on the test condition-component response characteristic fine-grained interaction encoding vector, it is determined whether the meteorological instrument under test fails.

2. The meteorological instrument fault detection method according to claim 1, characterized in that: The set of the core component response characteristic data is dynamically aggregated based on embedded coding to obtain a core component response characteristic significant aggregation coding vector, including: Each core component response characteristic data in the set of core component response characteristic data is passed through an embedding layer to obtain a set of core component response characteristic semantic embedding coding vectors; Calculating a pseudo-anchored aggregation center representation vector of a core component response characteristic based on a characteristic static potential energy distribution of a set of semantic embedding encoding vectors of the core component response characteristic; Calculating the aggregated motion direction of each core component response characteristic semantic embedding coding vector in the set of the core component response characteristic semantic embedding coding vectors relative to the core component response characteristic pseudo-anchored aggregated center representation vector to obtain a set of core component response characteristic aggregated motion directions; Based on the set of aggregation movement directions of the core component response characteristics, the set of the core component response characteristic semantic embedding coding vectors is dynamically aggregated toward the core component response characteristic pseudo-anchor aggregation center representation vector to obtain the core component response characteristic significant aggregation coding vector.

3. The meteorological instrument fault detection method according to claim 2, characterized in that: Based on the characteristic static potential energy distribution of the set of the semantic embedding coding vectors of the core component response characteristics, a pseudo-anchored aggregation center representation vector of the core component response characteristics is calculated, including: Inputting each core component response characteristic semantic embedding coding vector in the set of core component response characteristic semantic embedding coding vectors into a characteristic static potential energy measurement network to obtain a set of core component response characteristic static potential energy measurement coefficients; Inputting the set of core component response characteristic static potential energy measurement coefficients into a characteristic energy level screening gating unit to obtain a set of core component response characteristic static potential energy weight factors; Based on the set of static potential weight factors of the core component response characteristics, a weighted sum of the set of semantic embedding coding vectors of the core component response characteristics is calculated to obtain a pseudo-anchored aggregation center representation vector of the core component response characteristics.

4. The meteorological instrument fault detection method according to claim 3, characterized in that: Inputting each core component response characteristic semantic embedding coding vector in the set of core component response characteristic semantic embedding coding vectors into a characteristic static potential energy measurement network to obtain a set of core component response characteristic static potential energy measurement coefficients, including: Performing Z-score normalization processing on the core component response characteristic semantic embedding coding vector to obtain a normalized core component response characteristic semantic embedding coding vector; The sum of the cube of each eigenvalue in the standardized core component response characteristic semantic embedding coding vector is calculated and divided by the characteristic scale value of the standardized core component response characteristic semantic embedding coding vector to obtain the core component response characteristic static potential energy measurement coefficient.

5. The meteorological instrument fault detection method according to claim 4, characterized in that: The core component response characteristic aggregation movement direction is the arccosine function value between the core component response characteristic semantic embedding coding vector and the core component response characteristic pseudo-anchor aggregation center representation vector.

6. The meteorological instrument fault detection method according to claim 5, characterized in that: Performing feature fine-grained interaction based on external knowledge enhancement on the core component response characteristic significant aggregation coding vector and the test condition low-dimensional embedded coding vector to obtain a test condition-component response characteristic fine-grained interaction coding vector, including: Based on external knowledge, the core component response characteristic significant aggregation coding vector and the test condition low-dimensional embedding coding vector are optimized for feature interaction based on an attention mechanism to obtain an external knowledge optimized test condition-component response characteristic fine-grained interaction feature matrix; Optimize the test condition-component response characteristic fine-grained interactive feature matrix based on the external knowledge, perform feature modulation optimization on the core component response characteristic significant aggregation coding vector and the test condition low-dimensional embedded coding vector respectively to obtain an optimized core component response characteristic significant aggregation coding vector and an optimized test condition low-dimensional embedded coding vector; The test condition-component response characteristic fine-grained interaction coding vector is obtained by calculating the point-by-point division between the optimized core component response characteristic significant aggregation coding vector and the optimized test condition low-dimensional embedding coding vector.

7. The meteorological instrument fault detection method according to claim 6, characterized in that: Based on external knowledge, the core component response characteristic significant aggregation coding vector and the test condition low-dimensional embedding coding vector are optimized for feature interaction based on an attention mechanism to obtain an external knowledge optimized test condition-component response characteristic fine-grained interaction feature matrix, including: Inputting the core component response characteristic significant aggregation coding vector and the test condition low-dimensional embedding coding vector into a fine-grained feature interaction network to obtain a test condition-component response characteristic fine-grained interaction feature matrix; The test condition-component response characteristic fine-grained interaction feature matrix is ​​input into an attention unit based on external knowledge to obtain the external knowledge optimized test condition-component response characteristic fine-grained interaction feature matrix.

8. The meteorological instrument fault detection method according to claim 7, characterized in that: Optimizing the test condition-component response characteristic fine-grained interactive feature matrix based on the external knowledge, performing feature modulation optimization on the core component response characteristic significant aggregation coding vector and the test condition low-dimensional embedded coding vector respectively to obtain an optimized core component response characteristic significant aggregation coding vector and an optimized test condition low-dimensional embedded coding vector, including: Performing a linear transformation on the core component response characteristic significant aggregation coding vector to obtain a first query feature vector and a first value feature vector, and using the external knowledge optimization test condition-component response characteristic fine-grained interaction feature matrix as a key matrix, inputting the first query feature vector, the first value feature vector and the key matrix into a fine-grained modulation module based on a Transformer structure to obtain the optimized core component response characteristic significant aggregation coding vector; The test condition low-dimensional embedded coding vector is linearly transformed to obtain a second query feature vector and a second value feature vector, and the external knowledge-optimized test condition-component response characteristic fine-grained interaction feature matrix is ​​used as a key matrix. The second query feature vector, the second value feature vector and the key matrix are input into the Transformer-based fine-grained modulation module to obtain the optimized test condition low-dimensional embedded coding vector.

9. The meteorological instrument fault detection method according to claim 8, characterized in that: Determining whether a tested meteorological instrument fails based on the test condition-component response characteristic fine-grained interaction encoding vector includes: The test condition-component response characteristic fine-grained interactive coding vector is input into a classifier-based fault detection module to obtain a fault detection result, and the fault detection result is used to indicate whether the tested meteorological instrument has a fault.

10. A meteorological instrument fault detection system, characterized in that: include: A test condition setting module, used to set test conditions, wherein the test conditions include input voltage value, input current value and optical signal strength value; A response characteristic data acquisition module, used to acquire the response characteristic data of each core component of the tested meteorological instrument under the test conditions to obtain a set of core component response characteristic data; A test condition embedding coding module, used for embedding the test condition to obtain a low-dimensional embedding coding vector of the test condition; A feature dynamic aggregation processing module, used for performing feature dynamic aggregation based on embedded coding on the set of core component response characteristic data to obtain a core component response characteristic significant aggregation coding vector; A feature fine-grained interaction processing module, used for performing feature fine-grained interaction based on external knowledge enhancement on the core component response characteristic significant aggregation coding vector and the test condition low-dimensional embedded coding vector to obtain a test condition-component response characteristic fine-grained interaction coding vector; The meteorological instrument test result determination module is used to determine whether the meteorological instrument under test fails based on the test condition-component response characteristic fine-grained interactive coding vector.

Images