Star catalogue intelligent system failure analysis method and system of semi-supervised denoising auto-encoder

Abstract

The invention discloses a star catalogue intelligent system failure analysis method and system of a semi-supervised denoising auto-encoder, and relates to the technical field of fault detection. The method comprises the following steps: constructing a defect fault library of the star catalogue intelligent system according to the reason of the fault of the star catalogue intelligent system, and carrying out onhot coding on the fault state in the defect fault library; and receiving operation data of the star catalogue intelligent system in different states. According to the method, the advantages of supervised training and unsupervised training are combined, the accuracy and generalization ability of the model are improved by utilizing the accuracy of the marked data and the richness and low cost of the unmarked data and utilizing a large amount of unmarked data, and the original input data are damaged, so that the accuracy and generalization ability of the model are improved. More robust feature expression of nonlinear data can be completed through supervised training, and a Focal loss function is adopted, so that the phenomenon that the trained model shifts to a category with more samples due to imbalance between the samples can be avoided, and the model pays more attention to the category with less samples.

Description

Technical Field

[0001] The present invention relates to the technical field of fault detection, and in particular to a method and system for analyzing failure of a star table intelligent system of a semi-supervised denoising autoencoder. Background Art

[0002] As the demand for intelligent autonomy in satellite missions increases, the application of artificial intelligence methods in satellite mission spacecraft has become an inevitable trend. Whether it is the target recognition task during movement or the pose estimation task in operation control, the satellite mission process is simulated by human brain functions, such as perception, reasoning, judgment, learning and abstraction. This process has strong autonomy and can perform probabilistic reasoning under a given set of input conditions, resulting in a series of unexpected behaviors. Its generalization and evolutionary capabilities enable it to abstract its internal laws from complex data and have "growth" characteristics.

[0003] However, it is precisely because of these non-deterministic characteristics of artificial intelligence that it also brings significant failure risks to applications, which are specifically manifested in the following two points: (1) The autonomy and learning characteristics of intelligent technology itself make it more uncontrollable than other technologies. Faced with completely unknown human scenes, it is impossible to predict the output results of the intelligent algorithm in advance; (2) The risks caused by the imperfections of intelligent technology itself, such as the unexplainability of the decision-making process, susceptibility to interference, and learning unexpected decision-making routes, will all likely cause the task to deviate from the original established goals. Based on this, the failure mechanism of the star catalog intelligent model is an urgent problem that needs to be solved. Summary of the invention

[0004] The purpose of the present invention is to provide a method and system for analyzing the failure of a star-table intelligent system of a semi-supervised denoising autoencoder, which can solve the problem of unclear association between the cause of the failure and multi-dimensional data in view of software and algorithm failures that may be caused during the use of the star-table intelligent autonomous system.

[0005] According to the first aspect of the present invention, in order to achieve the above-mentioned purpose, the present invention provides the following technical solution: a method for failure analysis of a star table intelligent system of a semi-supervised denoising autoencoder, comprising the following steps: According to the causes of the star-table intelligent system failure, a defect fault library of the star-table intelligent system is constructed, and the fault states in the defect fault library are encoded ont_hot; Receive the operating data of the star catalog intelligent system in different states and pre-process the operating data; The preprocessed data and the corresponding running state codes constitute a sample data set, and the sample data set is divided into a training set and a test set; Construct a semi-supervised denoising autoencoder, which includes multiple layers of stacked sparse autoencoders, and introduce a Softmax classifier in the last layer of the semi-supervised denoising autoencoder; Input the training set data into the semi-supervised denoising autoencoder to optimize the model parameters and obtain the trained semi-supervised denoising autoencoder. The training process includes two parts: unsupervised pre-training and supervised fine-tuning. The test set data is input into the trained semi-supervised denoising autoencoder to realize online evaluation of the cause of system failure and calculate the precision and recall rate indicators of the model for the test set diagnosis.

[0006] Furthermore, the operating data includes ambient temperature, board temperature, board voltage, board current, program running time, number of correct instruction executions, error in the distance from the target position when the robotic arm executes instructions, confidence and accuracy of target detection, and the operating data are all collected during the test of the star chart intelligent system.

[0007] Furthermore, the operation data is preprocessed, specifically including the following methods: (31) Filling missing data values: Check whether the data value is empty. If the missing data accounts for a small proportion, ignore the missing data; if the missing data accounts for a large proportion, fill the missing data by filling the mean, median or mode of the missing column data; (32) Eliminate abnormal data values: Determine abnormal values. The detected abnormal data will be regarded as abnormal values ​​and deleted; (33) Delete redundant data: Calculate the similarity of the data. When the similarity exceeds the threshold, it is considered a duplicate record and deleted. (34) Data normalization: The Max-Min method was used for normalization, as follows: In the formula is the new data value, is the original data value, is the minimum value of all original data in the data set. is the maximum value of all original data in the data set; (35) Data dimensionality reduction: Principal component analysis is used to transform linearly correlated n-dimensional features into linearly independent k-dimensional comprehensive features through linear transformation.

[0008] Furthermore, a semi-supervised denoising autoencoder is constructed as follows: (41) Construct a traditional autoencoder model, which includes an input layer, a hidden layer, and an output layer. The number of nodes in the input layer is determined by the number of test data, and the number of nodes in the hidden layer and the output layer is determined by the dimension of the feature vector. (42) Construct a sparse autoencoder. Add a penalty factor term to the loss function of the traditional autoencoder model to restrict the sparsity of the traditional autoencoder model, and then construct a sparse autoencoder. The cost function of the sparse autoencoder is: In the formula, is the mean square error, To improve the mean square error, is the sparse penalty coefficient, set to 0.3, is the number of neurons in the hidden layer, is the Kullback-Leibler divergence, The neurons in the hidden layer For the average activation of all training data, is the sparsity parameter, set to 0.05 or 0.1, is the true label of the i-th sample, is the output value of the model, is the weight matrix, is the bias vector; (43) The sparse autoencoders are stacked according to a stack structure, and the output of the previous layer of the network is used as the input of the next layer of the network, thereby constructing a stacked sparse autoencoder; (44) Based on the stacked sparse autoencoder, noise is added to the original input data, and the changed data is input into the stacked sparse autoencoder to obtain a semi-supervised denoising autoencoder.

[0009] Furthermore, there are two ways to add noise to the original input data, as follows: (51) Add a Gaussian white noise, the formula is as follows: Where: is the data after adding noise; is the original data; is the coefficient; is a random number that follows a normal distribution with a mean of 0 and a variance of 1; (52) Randomly assign a portion of the components in the input vector to 0 with probability.

[0010] Furthermore, the training set data is input into the semi-supervised denoising autoencoder to optimize the model parameters and obtain the trained semi-supervised denoising autoencoder. The training process includes two parts: unsupervised pre-training and supervised fine-tuning, as follows: (61) Set the parameters of the semi-supervised denoising autoencoder, including the number of hidden layers and the number of neurons in each layer; The hidden layer is set to 2-5 layers, and the number of neurons in the hidden layer is calculated according to the following formula. The number of neurons in each hidden layer is the same: Where: is the number of neurons in the hidden layer, is the number of test set samples, is the number of input neurons, is the number of output neurons; is an arbitrary value variable, with a specific value range of 1 to 5; (62) Perform unsupervised pre-training on each sparse autoencoder, using unlabeled data samples, and using the loss function in step (42), adopting a layer-by-layer greedy training method and a back propagation algorithm, and sequentially training the network parameters of each layer of the semi-supervised denoising autoencoder; (63) In the supervised fine-tuning stage, multiple supervised sparse autoencoders are stacked up in a stacked structure to form a semi-supervised denoising autoencoder. That is, the hidden layer features of the previous supervised sparse autoencoder are used as the input information of the next one. The decoding layer of the semi-supervised denoising autoencoder is removed, and a Softmax classification layer is added. The Focal loss function is used to optimize the network parameters of each layer using the back propagation algorithm. The Focal loss function is expressed as follows: Where: F represents the Focal loss function, is the balance parameter, is the focusing parameter, is the predicted label probability.

[0011] According to a second aspect of the present invention, the present invention provides a semi-supervised denoising autoencoder star table intelligent system failure analysis system, which is used to implement the above-mentioned semi-supervised denoising autoencoder star table intelligent system failure analysis method, comprising: The defect fault library construction module is used to construct the defect fault library of the star table intelligent system according to the cause of the star table intelligent system failure, and to perform ont_hot coding on the fault status in the defect fault library; A data preprocessing module is used to receive the operating data of the star catalog intelligent system in different states and preprocess the operating data; A data set division module is used to form a sample data set by combining the preprocessed data and the corresponding running state code, and divide the sample data set into a training set and a test set; The building module is used to build a semi-supervised denoising autoencoder. The fault diagnosis model includes a multi-layer stacked sparse autoencoder, and the last layer of the fault diagnosis model introduces a Softmax classifier; The training module is used to input the training set data into the semi-supervised denoising autoencoder to optimize the model parameters and obtain the trained semi-supervised denoising autoencoder. The training process includes two parts: unsupervised pre-training and supervised fine-tuning. The test output module is used to input the test set data into the trained semi-supervised denoising autoencoder to achieve online evaluation of the cause of system failure and calculate the model's precision and recall indicators for the test set diagnosis.

[0012] According to a third aspect of the present invention, the present invention provides a terminal device, comprising a memory, a processor, and a computer program stored in the memory and capable of running on the processor, wherein the memory stores a computer program capable of running on the processor, and when the processor loads and executes the computer program, the star catalog intelligent system failure analysis method of the above-mentioned semi-supervised denoising autoencoder is adopted.

[0013] According to a fourth aspect of the present invention, the present invention provides a storage medium comprising computer executable instructions, which, when executed by a computer processor, are used to execute the above-mentioned semi-supervised denoising autoencoder star catalog intelligent system failure analysis method.

[0014] According to a fifth aspect of the present invention, the present invention provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it is used to load and execute the above-mentioned semi-supervised denoising autoencoder star catalog intelligent system failure analysis method.

[0015] The present invention has at least the following beneficial effects: 1. The semi-supervised training adopted in the present invention combines the advantages of supervised training and unsupervised training, utilizing the accuracy of labeled data and the richness and low cost of unlabeled data, and utilizing a large amount of unlabeled data to improve the accuracy and generalization ability of the model. By damaging the original input data, supervised training can achieve a more robust feature expression for nonlinear data, thereby improving the robustness of the model.

[0016] 2. The Focal loss function adopted in the present invention can avoid the deviation of the trained model to the category with more samples due to the imbalance between samples, so that the model pays more attention to the category with fewer samples, thereby improving the accuracy of the model in diagnosing faults of the star catalog intelligent system.

[0017] 3. Introducing Gaussian white noise into the input vector in the present invention helps prevent model overfitting and can enhance the generalization performance of the model.

[0018] Of course, any product implementing the present invention does not necessarily need to achieve all of the advantages described above at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] Figure 1 is a flow chart of the analysis method described in an embodiment of the present invention; Figure 2 This is a schematic diagram of the framework of the analysis method described in the embodiment of the present invention; Figure 3 A schematic diagram of a defect fault library of a star table intelligent system constructed in an embodiment of the present invention; Figure 4 Schematic diagram of the structure of the autoencoder in an embodiment of the present invention; Figure 5 Schematic diagram of the structure of a stacked sparse autoencoder in an embodiment of the present invention. DETAILED DESCRIPTION

[0020] The following will be combined with the drawings in the embodiments of the present disclosure to clearly and completely describe the technical solutions in the embodiments of the present disclosure. Obviously, the described embodiments are only part of the embodiments of the present disclosure, not all of the embodiments. Based on the embodiments in the present disclosure, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present disclosure.

[0021] The present invention proposes a method for analyzing the failure of a star-table intelligent system using a semi-supervised denoising autoencoder. Aiming at the failure phenomenon caused by software, algorithms, etc. in the star-table intelligent system, a data-driven method is used to analyze the cause of the system failure and determine the key defect factors of the star-table intelligent system. The operating data of the star-table intelligent system under different states is collected and pre-processed to construct the training set and test set of the model; the training set is input into the semi-supervised denoising autoencoder (SSDAE) for training to obtain the star-table intelligent system software failure mechanism analysis model (the trained semi-supervised denoising autoencoder); the trained model is used to analyze the mechanism of software failure, and finally the analysis results of software failure are output.

[0022] See also Figure 1 and Figure 2 The present invention provides a technical solution: a method for analyzing the failure of a star table intelligent system of a semi-supervised denoising autoencoder, comprising the following steps: S1. According to the causes of the star table intelligent system failure, a defect fault library of the star table intelligent system is constructed, and various operating states (including normal states and various fault states) in the defect fault library are ont_hot encoded; like Figure 3As shown, the defect fault library includes fault states caused by software, algorithms, etc., among which software defect faults include software design errors, software programming errors, external input errors, exception handling errors, etc.; algorithm defect faults include sample data set size is too small, sample annotation quality is low, there is no verification set and test set data, pre-processing data method is wrong, etc.; Various fault states such as software defect faults and algorithm defect faults are encoded using ont_hot as shown in the following table. For example, the normal state symbol bit N, the state encoding is (1, 0, 0, 0, 0, 0, ..., 0), as shown in Table 1 below: Table 1 is the running status code table ; S2. Receive the operation data of the star table intelligent system in different states (including normal state and various fault states), and pre-process the operation data; It should be noted that the operating data (raw data) are collected during the test of the Star Table Intelligent System. The operating data are data under different operating conditions, such as ambient temperature, board temperature, board voltage, board current, program running time, number of correct execution instructions, error of the robot arm from the target position when executing instructions, and other parameters. These process variable parameters are used as the input of the model after data preprocessing. The preprocessing mainly includes the following methods: S21. Fill in missing data values: Check whether the data value is empty. If the missing data accounts for a small proportion, the missing data can be ignored; if it is very important data, the missing data can be supplemented by filling the missing column data with the mean, median or mode. S22. Eliminate abnormal data values: Z-score, interquartile range or clustering methods can be used to determine abnormal values. The detected abnormal data will be regarded as abnormal values ​​and deleted; S23. Delete redundant data: Euclidean distance, cosine similarity and other methods can be used to calculate the similarity of data. When the similarity exceeds a certain threshold, it is considered to be a duplicate record and the duplicate record will be deleted; S24. Data standardization: In order to eliminate the impact of dimensions between features and make them comparable, Max-Min normalization is generally used, which is achieved through the following formula: In the formula is the new data value, is the original data value, is the minimum value of all original data in the data set. is the maximum value of all original data in the data set; S25. Data Dimensionality Reduction: The principal component analysis method can be used to transform the linearly correlated n-dimensional features into linearly independent k-dimensional comprehensive features through a linear transformation, and use the linearly independent k-dimensional comprehensive features to represent the information represented by the linearly correlated n-dimensional features. The linear transformation is the process of projecting the n-dimensional linearly correlated features onto the k-dimensional linearly independent comprehensive features through the linear transformation basis; S3. Construct a sample data set by combining the preprocessed data with the corresponding operating state codes, and divide the sample data set into a training set and a test set; For the data of each type of operating state, divide the data set into a training sample set and a test sample set according to a ratio of 7:3. The training sample set is used to train the deep learning model, and the test set is used to test and evaluate the performance of the neural network; At this time, the input of the fault diagnosis model is the preprocessed standardized data, and the output is the system operating state code; S4. Construct a semi-supervised denoising autoencoder (fault diagnosis model). The semi-supervised denoising autoencoder includes multiple stacked sparse autoencoders, and a Softmax classifier is introduced in the last layer of the semi-supervised denoising autoencoder, specifically as follows: S41. Construct a traditional autoencoder model (Autoencoder, AE), which includes an input layer, a hidden layer, and an output layer. The number of nodes in the input layer is determined according to the number of test data, and the number of nodes in the hidden layer and the output layer is determined according to the dimension of the feature vector, as Figure 4 shown; Specifically, it includes two stages. The first stage is the encoding stage, which converts the original input data type of the model into the internal data type of the encoder; the second stage is the decoding stage, which converts the internal data type of the encoder into the model output data type. The number of nodes in the input layer is determined according to the number of the test data, and the number of nodes in the hidden layer and the output layer is determined according to the dimension of the feature vector; Assume that the input training sample data set of the autoencoder is , where N represents the total number of samples, the number of neurons in the input layer and the output layer is both n, the number of neurons in the hidden layer is m, the input vector expression is , the output vector expression is , the hidden layer vector expression is , where m < n, then the corresponding encoding and decoding processes can be represented by the following formulas respectively: In the formula: represents the encoding weight matrix between the input layer and the hidden layer, represents the encoding bias vector between the input layer and the hidden layer; Represents the decoding weight matrix from the hidden layer to the output layer, Represents the decoding bias vector between the hidden layer and the output layer; and Respectively represent the nonlinear activation functions of the encoding and decoding processes; the construction process uses the Relu function as the activation function, which has the advantage of not having the gradient vanishing problem and can ensure that the convergence speed of the autoencoder model remains in a stable state. The formula is as follows: ; S42. Construct a sparse auto-encoder (SAE), add a penalty factor term to the loss function of the traditional auto-encoder model, restrict the sparsity of the traditional auto-encoder model, and then construct a sparse auto-encoder (SAE). The cost function of the sparse auto-encoder is: In the formula, is the mean square error; To improve the mean square error; is the sparse penalty coefficient, which can generally be set to 0.3; is the number of neurons in the hidden layer; is the Kullback-Leibler divergence; The neurons in the hidden layer The average activation of all training data; is the sparsity parameter, which can generally be set to 0.05 or 0.1; is the true label of the i-th sample; is the output value of the model; is the weight matrix; is the bias vector; S43. The sparse auto-encoders are stacked according to a stack structure, and the output of the previous layer of the network is used as the input of the next layer of the network, thereby constructing a stack sparse auto-encoder (SSAE); S44. Figure 5As shown in the figure, on the basis of the stacked sparse autoencoder, noise is added to the original input data, and the changed data is input into the stacked sparse autoencoder to obtain a semi-supervised denoising autoencoder (stack sparse denoising auto-encoder, SSDAE), which can also be called a stacked sparse denoising autoencoder. The stacked sparse denoising autoencoder is a model of the semi-supervised denoising autoencoder in the unsupervised pre-training stage; There are two ways to add noise to the original input data, as follows: (S44.1) Add a Gaussian white noise, the formula is as follows: Where: is the data after adding noise; is the original data; is the coefficient; is a random number that follows a normal distribution with a mean of 0 and a variance of 1; (S44.2) Randomly assigning a portion of the input vector to 0 according to probability, SSDAE forces the encoder to learn to extract important features and learn more robust features in the input data, while increasing the generalization ability of the model; S5. Input the training set data into the semi-supervised denoising autoencoder to optimize the model parameters and obtain the trained semi-supervised denoising autoencoder. The training process includes two parts: unsupervised pre-training and supervised fine-tuning, as follows: S51. Set the parameters of the semi-supervised denoising autoencoder, including the number of hidden layers and the number of neurons in each layer; The hidden layer is set to 2-5 layers, and the number of neurons in the hidden layer is calculated according to the following formula. The number of neurons in each hidden layer is the same: Where: is the number of neurons in the hidden layer, is the number of test set samples, is the number of input neurons, is the number of output neurons; is an arbitrary value variable, with a specific value range of 1 to 5; S52. Perform unsupervised pre-training on each sparse autoencoder, using unlabeled data samples, and using the loss function in step S42, adopting a layer-by-layer greedy training method and a back propagation algorithm, and sequentially training each layer of the network parameters of the semi-supervised denoising autoencoder; Specifically, the unsupervised process is composed of N sparse autoencoders, each of which consists of 3 layers: input layer + hidden layer + output layer. The unsupervised process consists of N input layers + hidden layers + output layers; S53. In the supervised fine-tuning stage, multiple supervised sparse autoencoders are stacked up according to a stack structure to form a semi-supervised denoising autoencoder, that is, the hidden layer features of the previous supervised sparse autoencoder are used as the input information of the next one, the decoding layer of the semi-supervised denoising autoencoder is removed, and a Softmax classification layer is added. The Focal loss function is used, and the back propagation algorithm is used to optimize the network parameters of each layer; The supervised fine-tuning process is: the first input layer + the first hidden layer + the second input layer + the second hidden layer + the third input layer + the third hidden layer + ... the Nth input layer + the Nth hidden layer + the Nth output layer + the softmax classification layer; The use of the Focal loss function can avoid the deviation of the trained model to the category with more samples due to the imbalance between samples (normal data samples account for a large proportion and fault data samples account for a small proportion). The Focal loss function is expressed as follows: Where: F represents the Focal loss function, which represents is the balance parameter, is the focusing parameter, To predict label probability; It should be noted that the entire training process is called semi-supervised, which is a combination of unsupervised pre-training and supervised fine-tuning, a total of two processes, and the model of supervised fine-tuning training is further improved on the basis of the model used in unsupervised pre-training. After completing the two stages of training, the semi-supervised denoising autoencoder can be obtained; S6. Input the test set data into the semi-supervised denoising autoencoder model to realize the online evaluation of the failure mechanism model of the star table intelligent autonomous system and evaluate the training results. In addition, evaluation indicators such as precision, recall, and F1 value can be introduced to further analyze and evaluate the online evaluation results of the model.

[0023] In summary, the present invention collects the operating data of the star table intelligent system under different states during the test, performs pre-processing such as filling missing values, eliminating outliers, and standardizing the data, and performs ont_hot encoding on the fault type, and randomly classifies each type of operating status data in proportion, and divides it into a training sample set and a test sample set; adopts a two-stage training, firstly, unsupervised pre-training is performed on each SAE, and unlabeled data samples are used, and a layer-by-layer greedy training method and a back propagation algorithm are adopted to train each layer of network parameters of the SSDAE model in turn; secondly, there is a supervised fine-tuning stage, in which multiple supervised SAEs are stacked up according to a stack structure to form an SSDAE, and a Softmax classification layer is added, and a Focal loss function is used. The back propagation algorithm is used to optimize the network parameters of each layer, and finally the test sample data set is input into the semi-supervised denoising autoencoder model to realize the online evaluation of the failure mechanism model of the star table intelligent autonomous system and analyze the real-time operating status of the star table intelligent system.

[0024] Embodiment 2: This embodiment provides a semi-supervised denoising autoencoder star table intelligent system failure analysis system, which is used to implement the semi-supervised denoising autoencoder star table intelligent system failure analysis method described in Embodiment 1, including: The defect fault library construction module is used to construct the defect fault library of the star table intelligent system according to the cause of the star table intelligent system failure, and to perform ont_hot coding on the fault status in the defect fault library; A data preprocessing module is used to receive the operating data of the star catalog intelligent system in different states and preprocess the operating data; A data set division module is used to form a sample data set by combining the preprocessed data and the corresponding running state code, and divide the sample data set into a training set and a test set; The building module is used to build a semi-supervised denoising autoencoder. The fault diagnosis model includes a multi-layer stacked sparse autoencoder, and the last layer of the fault diagnosis model introduces a Softmax classifier; The training module is used to input the training set data into the semi-supervised denoising autoencoder to optimize the model parameters and obtain the trained semi-supervised denoising autoencoder. The training process includes two parts: unsupervised pre-training and supervised fine-tuning. The test output module is used to input the test set data into the trained semi-supervised denoising autoencoder to achieve online evaluation of the cause of system failure and calculate the model's precision and recall indicators for the test set diagnosis.

[0025] Specifically, the above-mentioned defect fault library construction module, data preprocessing module, data set division module, construction module, training module and test output module can be embedded in a computer processing system. The computer calls the above-mentioned modules to complete the task of fault diagnosis of the star catalog intelligent system based on the above-mentioned semi-supervised denoising autoencoder star catalog intelligent system failure analysis method; the above-mentioned defect fault library construction module, data preprocessing module, data set division module, construction module, training module and test output module can perform operations according to the specific steps given in the above-mentioned semi-supervised denoising autoencoder star catalog intelligent system failure analysis method.

[0026] It should be noted that it should be understood that the division of the various modules of the above system is only the division of logical functions. In actual implementation, they can be fully or partially integrated into one physical entity, or they can be physically separated, and these modules can all be implemented in the form of software calling through processing elements; they can also be all implemented in the form of hardware; some modules can also be implemented in the form of software calling through processing elements, and some modules can be implemented in the form of hardware. For example, the shared remote driving system building module can be a separately established processing element, or it can be integrated in a chip of the above-mentioned device. In addition, it can also be stored in the memory of the above-mentioned device in the form of program code, and a processing element of the above-mentioned device calls and executes the functions of the above signal processing module. The implementation of other modules is similar. In addition, all or part of these modules can be integrated together, or they can be implemented independently. The processing element described here can be an integrated circuit with signal processing capabilities. In the implementation process, each step of the above method or each of the above modules can be completed by the hardware integrated logic circuit in the processor element or the instructions in the form of software.

[0027] For example, the above modules can be configured as one or more integrated circuits for implementing the above methods, such as: one or more application specific integrated circuits (ASIC), or one or more digital singnal processors (DSP), or one or more field programmable gate arrays (FPGA). For another example, when a module above is implemented in the form of a processing element scheduling program code, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processors that can call program codes. For another example, these modules can be integrated together and implemented in the form of a system-on-a-chip (SOC).

[0028] Embodiment three: The present invention provides a computer program product, which includes a computer program. When the computer program is executed by a processor, it is used to load and execute the above-mentioned star catalog intelligent system failure analysis method of the semi-supervised denoising autoencoder.

[0029] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0030] For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to the specific circumstances. When an element is referred to as being "assembled on", "installed on", "fixed on" or "set on" another element, it can be directly on the other element or there can also be a centered element. When an element is considered to be "connected" to another element, it can be directly connected to the other element or there may be a centered element at the same time. The terms "vertical", "horizontal", "up", "down", "left", "right" and similar expressions used herein are only for illustrative purposes and are not intended to be the only implementation method.

[0031] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

[0032] In the description of this specification, the description with reference to the terms "one embodiment", "example", "specific example", etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present disclosure. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

Claims

1. A method for failure analysis of a star-table intelligent system based on a semi-supervised denoising autoencoder, characterized in that: The following steps are involved: According to the causes of the star-table intelligent system failure, a defect fault library of the star-table intelligent system is constructed, and the fault states in the defect fault library are encoded ont_hot; Receive the operating data of the star catalog intelligent system in different states and pre-process the operating data; The preprocessed data and the corresponding running state codes constitute a sample data set, and the sample data set is divided into a training set and a test set; Construct a semi-supervised denoising autoencoder, which includes multiple layers of stacked sparse autoencoders, and introduce a Softmax classifier in the last layer of the semi-supervised denoising autoencoder; Input the training set data into the semi-supervised denoising autoencoder to optimize the model parameters and obtain the trained semi-supervised denoising autoencoder. The training process includes two parts: unsupervised pre-training and supervised fine-tuning. The test set data is input into the trained semi-supervised denoising autoencoder to realize online evaluation of the cause of system failure and calculate the precision and recall rate indicators of the model for the test set diagnosis.

2. The method for failure analysis of a star table intelligent system of a semi-supervised denoising autoencoder according to claim 1, characterized in that: The operating data include ambient temperature, board temperature, board voltage, board current, program running time, number of correct instruction executions, error in the distance from the target position when the robotic arm executes instructions, confidence and accuracy of target detection. The operating data are all collected during the test of the star table intelligent system.

3. The method for failure analysis of a star table intelligent system of a semi-supervised denoising autoencoder according to claim 1, characterized in that: Preprocess the running data, including the following methods: (31) Filling missing data values: Check whether the data value is empty. If the missing data accounts for a small proportion, ignore the missing data; if the missing data accounts for a large proportion, fill the missing data by filling the mean, median or mode of the missing column data; (32) Eliminate abnormal data values: Determine abnormal values. The detected abnormal data will be regarded as abnormal values ​​and deleted; (33) Deleting redundant data: Calculate the similarity of the data. When the similarity exceeds the threshold, it is considered a duplicate record and deleted. (34) Data normalization: The Max-Min method was used for normalization, as follows: In the formula is the new data value, is the original data value, is the minimum value of all original data in the data set. is the maximum value of all original data in the data set; (35) Data dimensionality reduction: Principal component analysis is used to transform linearly correlated n-dimensional features into linearly independent k-dimensional comprehensive features through linear transformation.

4. The method for failure analysis of a star table intelligent system of a semi-supervised denoising autoencoder according to claim 3, characterized in that: Construct a semi-supervised denoising autoencoder as follows: (41) Construct a traditional autoencoder model, which includes an input layer, a hidden layer, and an output layer. The number of nodes in the input layer is determined by the number of test data, and the number of nodes in the hidden layer and the output layer is determined by the dimension of the feature vector. (42) Construct a sparse autoencoder. Add a penalty factor term to the loss function of the traditional autoencoder model to restrict the sparsity of the traditional autoencoder model, and then construct a sparse autoencoder. The cost function of the sparse autoencoder is: In the formula, is the mean square error; To improve the mean square error; is the sparse penalty coefficient, set to 0.3; is the number of neurons in the hidden layer; is the Kullback-Leibler divergence; The neurons in the hidden layer The average activation of all training data; is the sparsity parameter, set to 0.05 or 0.1; is the true label of the i-th sample; is the output value of the model; is the weight matrix; is the bias vector; (43) The sparse autoencoders are stacked according to a stack structure, and the output of the previous layer of the network is used as the input of the next layer of the network, thereby constructing a stacked sparse autoencoder; (44) Based on the stacked sparse autoencoder, noise is added to the original input data, and the changed data is input into the stacked sparse autoencoder to obtain a semi-supervised denoising autoencoder.

5. The method for failure analysis of a star table intelligent system of a semi-supervised denoising autoencoder according to claim 4, characterized in that: There are two ways to add noise to the original input data, as follows: (51) Add a Gaussian white noise, the formula is as follows: Where: is the data after adding noise; is the original data; is the coefficient; is a random number that follows a normal distribution with a mean of 0 and a variance of 1; (52) Randomly assign a portion of the components in the input vector to 0 with probability.

6. The method for failure analysis of a star table intelligent system of a semi-supervised denoising autoencoder according to claim 5, characterized in that: The training set data is input into the semi-supervised denoising autoencoder to optimize the model parameters and obtain the trained semi-supervised denoising autoencoder. The training process includes two parts: unsupervised pre-training and supervised fine-tuning, as follows: (61) Set the parameters of the semi-supervised denoising autoencoder, including the number of hidden layers and the number of neurons in each layer; The hidden layer is set to 2-5 layers, and the number of neurons in the hidden layer is calculated according to the following formula. The number of neurons in each hidden layer is the same: Where: is the number of neurons in the hidden layer, is the number of test set samples, is the number of input neurons, is the number of output neurons; is an arbitrary value variable, with a specific value range of 1 to 5; (62) Perform unsupervised pre-training on each sparse autoencoder, using unlabeled data samples, and using the loss function in step (42), adopting a layer-by-layer greedy training method and a back propagation algorithm, and sequentially training the network parameters of each layer of the semi-supervised denoising autoencoder; (63) In the supervised fine-tuning stage, multiple supervised sparse autoencoders are stacked up in a stacked structure to form a semi-supervised denoising autoencoder. That is, the hidden layer features of the previous supervised sparse autoencoder are used as the input information of the next one. The decoding layer of the semi-supervised denoising autoencoder is removed, and a Softmax classification layer is added. The Focal loss function is used to optimize the network parameters of each layer using the back propagation algorithm. The Focal loss function is expressed as follows: Where: F represents the Focal loss function, is the balance parameter, is the focusing parameter, is the predicted label probability.

7. A semi-supervised denoising autoencoder star table intelligent system failure analysis system, used to implement the semi-supervised denoising autoencoder star table intelligent system failure analysis method according to any one of claims 1 to 6, characterized in that: include: The defect fault library construction module is used to construct the defect fault library of the star table intelligent system according to the cause of the star table intelligent system failure, and to perform ont_hot coding on the fault status in the defect fault library; A data preprocessing module is used to receive the operating data of the star catalog intelligent system in different states and preprocess the operating data; A data set division module is used to form a sample data set by combining the preprocessed data and the corresponding running state code, and divide the sample data set into a training set and a test set; The building module is used to build a semi-supervised denoising autoencoder. The fault diagnosis model includes a multi-layer stacked sparse autoencoder, and the last layer of the fault diagnosis model introduces a Softmax classifier; The training module is used to input the training set data into the semi-supervised denoising autoencoder to optimize the model parameters and obtain the trained semi-supervised denoising autoencoder. The training process includes two parts: unsupervised pre-training and supervised fine-tuning. The test output module is used to input the test set data into the trained semi-supervised denoising autoencoder to achieve online evaluation of the cause of system failure and calculate the model's precision and recall indicators for the test set diagnosis.

8. A computer program product, characterized in that The computer program product comprises a computer program, which, when executed by a processor, is used to load and execute the star-table intelligent system failure analysis method of the semi-supervised denoising autoencoder according to any one of claims 1 to 6.

Images