Equipment fault diagnosis method and device based on sensor data

Abstract

The invention provides an equipment fault diagnosis method and device based on sensor data, and relates to the technical field of data processing, after chaotic randomization feature extraction is carried out on operation state data of equipment to be detected through a pre-trained neural network, classification and identification are carried out through a fault diagnosis model, and a fault diagnosis result of the equipment is determined. Chaotic randomization feature extraction is beneficial to breaking the limitation of a local optimal solution and increasing the possibility of exploring different solutions, in addition, the neural network used for chaos randomization feature extraction is constructed based on self-organization feedback, neurons of the neural network effectively cooperate, the network can be helped to better learn the internal structure in data, and the algorithm efficiency is improved. According to the method, the dynamic change and the nonlinear relation in the data can be more accurately captured, the distribution characteristics of the characteristic space of the data can be fully utilized, and the fault identification effect is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular, to a device fault diagnosis method and device based on sensor data. Background Art

[0002] With the wide application of industrial equipment, the monitoring of the operating state and fault diagnosis of equipment have become important means to ensure the safety and reliability of industrial systems. Faults in industrial equipment can not only lead to production interruptions but also may cause safety accidents. Therefore, an efficient and accurate fault diagnosis method is needed to reduce potential risks.

[0003] Among them, there are many challenges in data acquisition, processing, and analysis in device fault diagnosis. The operating environment of the device is complex and changeable, and the data characteristics change over time. However, existing feature extraction methods often cannot reflect these changes in real time or effectively, making it difficult to effectively capture the changes in data, resulting in the feature extraction results being unable to accurately represent the actual operating conditions of the device. In addition, the data generated by the device is usually multi-dimensional and interrelated. When existing technologies perform feature extraction, they often process each feature separately, ignoring the internal connections between features. This may lead to incomplete feature information extraction, affecting the accuracy of subsequent analysis and fault diagnosis.

[0004] In addition, in the process of high-dimensional data classification, effective feature space analysis can help identify data patterns and abnormal situations. However, existing methods usually only focus on dimensionality reduction or simply apply some general preprocessing steps, failing to deeply mine the structural information of the feature space and make full use of the distribution characteristics of the feature space, resulting in insufficient model generalization ability and poor fault recognition effect for unknown device states. Summary of the Invention

[0005] To solve the above technical problems, embodiments of the present invention provide a device fault diagnosis method and device based on sensor data, which can more accurately capture the dynamic changes and non-linear relationships in the data, and make full use of the distribution characteristics of the feature space of the data to improve the effect of fault recognition.

[0006] In a first aspect, embodiments of the present invention provide a device fault diagnosis method based on sensor data, the method includes: obtaining the operating state data of a device to be measured; using a pre-trained neural network to perform chaotic randomization feature extraction on the operating state data to determine the target features of the operating state data; wherein, the neural network is constructed based on self-organizing feedback; inputting the target features into a preset fault diagnosis model to determine the fault classification result corresponding to the target features; and determining the fault state of the device to be measured based on the fault classification result.

[0007] Combined with the first aspect, the embodiments of the present invention provide a first implementation manner of the first aspect. Among them, the steps of using a pre-trained neural network to perform chaotic randomization feature extraction on the operating state data and determining the target features of the operating state data include: inputting the operating state data into a preset neural network, performing chaotic randomization search on the operating state data based on the oscillation states of the neurons of the neural network, and determining the neuron outputs corresponding to each neuron of the neural network; determining the self-organizing feedback amount corresponding to the neural network according to the neuron output of each neuron; adjusting the neuron output according to the self-organizing feedback amount to determine the target features of the operating state data.

[0008] Combined with the first aspect, the embodiments of the present invention provide a second implementation manner of the first aspect. Among them, the steps of inputting the operating state data into a preset neural network, performing chaotic randomization search on the operating state data based on the oscillation states of the neurons of the neural network, and determining the neuron outputs corresponding to each neuron of the neural network include: obtaining the oscillation parameters of the neurons of the neural network, performing chaotic randomization search on the operating state data based on the oscillation parameters, and determining the neuron outputs corresponding to the neural network.

[0009] Combined with the first aspect, the embodiments of the present invention provide a third implementation manner of the first aspect. Among them, the calculation method of the oscillation parameters of the neurons includes: using a preset chaotic function to perform chaotic random initialization on the initial weights and biases of the neural network; where the chaotic function includes preset oscillation phases and angle parameters; setting the initial oscillation frequencies and amplitudes of the neurons of the neural network based on the oscillation phases and preset oscillation control parameters; inputting a preset training sample set into the neural network to adaptively adjust the initial oscillation frequencies and amplitudes; and iterating the preset oscillation phases and angle parameters based on the chaotic perturbation terms corresponding to the oscillation phases; until the neural network meets the preset training requirements to obtain the final oscillation parameters of the neurons.

[0010] Combined with the first aspect, the embodiments of the present invention provide a fourth implementation manner of the first aspect. Among them, the steps of adjusting the neuron output according to the self-organizing feedback amount to determine the target features of the operating state data include: updating the weight parameters of the neural network based on the self-organizing feedback amount to adjust the neuron output.

[0011] Combined with the first aspect, an embodiment of the present invention provides a fifth implementation manner of the first aspect. Among them, the method for constructing a preset training sample set includes: acquiring pre-collected device operation monitoring data; performing data annotation on the device operation monitoring data according to the device operation state indicated by the device operation monitoring data to construct an initial sample set; determining the feature distribution of the initial sample set; based on the feature distribution, determining the target position to be augmented in the initial sample set; performing data augmentation on the target position to be augmented through a preset sample augmentation algorithm to obtain augmented samples; and combining the augmented samples and the initial sample set to construct a training sample set.

[0012] Combined with the first aspect, an embodiment of the present invention provides a sixth implementation manner of the first aspect. Among them, the step of determining the target augmentation position in the initial sample set based on the feature distribution includes: determining the sample augmentation weight of the minority class samples corresponding to the initial sample set based on the feature distribution; and determining the target position to be augmented corresponding to each sample according to the sample augmentation weight and the Euclidean distance between each sample in the initial sample set.

[0013] Combined with the first aspect, an embodiment of the present invention provides a seventh implementation manner of the first aspect. Among them, the step of performing data augmentation on the target position to be augmented through a preset sample augmentation algorithm to obtain augmented samples includes: performing data interpolation on the position to be augmented based on the sample augmentation weight to generate the augmented samples corresponding to the current samples.

[0014] Combined with the first aspect, an embodiment of the present invention provides an eighth implementation manner of the first aspect. Among them, the step of determining the feature distribution of the initial sample set includes: determining the feature mean of the initial sample set, and calculating the feature standard deviation of the initial sample set based on the feature mean; and performing feature space normalization processing on the initial sample set based on the feature standard deviation to determine the feature distribution of the initial sample set.

[0015] In the second aspect, an embodiment of the present invention provides a device for diagnosing device faults based on sensor data. The device includes: a data acquisition module for acquiring the operation state data of the device to be measured; a data processing module for extracting chaotic randomization features from the operation state data by using a pre-trained neural network to determine the target features of the operation state data, where the neural network is constructed based on self-organization feedback; an execution module for inputting the target features into a preset fault diagnosis model to determine the fault classification result corresponding to the target features; and an output module for determining the fault state of the device to be measured based on the fault classification result.

[0016] The embodiments of the present invention bring the following beneficial effects: A method and device for diagnosing equipment faults based on sensor data provided by the embodiments of the present invention can break through the limitation of local optimal solutions, effectively identify the internal structure of data, more accurately capture the dynamic changes and non-linear relationships in the data, so as to obtain more accurate target features. Thus, it can make full use of the distribution characteristics of the feature space of the data, adapt to the characteristics of different data sets or the changes in the equipment state for fault identification, and improve the effect of fault identification.

[0017] Other features and advantages of the present invention will be described in the following specification, and part of them will become obvious from the specification or be understood by implementing the present invention. The objectives and other advantages of the present invention are achieved and obtained by the structures specifically pointed out in the specification, claims and drawings.

[0018] To make the above objectives, features and advantages of the present invention more obvious and understandable, the following specific preferred embodiments are given and described in detail in conjunction with the accompanying drawings as follows. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the following drawings are some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0020] Figure 1 It is a flowchart of a method for diagnosing equipment faults based on sensor data provided by an embodiment of the present invention; Figure 2 It is a flowchart of another method for diagnosing equipment faults based on sensor data provided by an embodiment of the present invention; Figure 3 It is a schematic diagram showing the influence of different initialization methods on the training loss provided by an embodiment of the present invention; Figure 4 It is a schematic diagram comparing the performance of different algorithms under noisy data provided by an embodiment of the present invention; Figure 5 It is a flowchart of a method for constructing a training sample set provided by an embodiment of the present invention; Figure 6 It is a schematic structural diagram of a device for diagnosing equipment faults based on sensor data provided by an embodiment of the present invention; Figure 7 It is a schematic structural diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be described clearly and completely below in conjunction with the embodiments. Apparently, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0022] The embodiments of the present invention provide a method and device for diagnosing equipment faults based on sensor data, which can more accurately capture the dynamic changes and non-linear relationships in the data and make full use of the distribution characteristics of the feature space of the data to improve the effect of fault identification.

[0023] To facilitate the understanding of this embodiment, first, a method for diagnosing equipment faults based on sensor data disclosed in the embodiments of the present invention will be introduced in detail. Refer to Figure 1 the schematic flowchart of a method for diagnosing equipment faults based on sensor data shown in the figure. The method may include the following steps: Step S102: Obtain the operation status data of the device to be measured.

[0024] The data collection source of the present invention is sensors installed on various industrial devices, including but not limited to temperature sensors, vibration sensors, and pressure sensors. These sensors can monitor the operation status of the device in real time and collect key performance parameters. Among them, sensors can be installed at key parts of the device according to the operation characteristics and monitoring requirements of the device. For example, temperature sensors are installed near components that may generate heat; vibration sensors are fixed on the mechanical main structure to monitor the vibration level during device operation; pressure sensors are installed on pipelines where liquid or gas pressure needs to be monitored; current and voltage sensors are connected to the power supply line. The sensors monitor various parameters of the device in real time and convert the collected device data into electrical signals. These electrical signals are converted into digital signals through an analog-to-digital converter and then undergo preliminary processing, such as filtering, amplification, and device data formatting, in the microcontroller unit of the sensor. Further, the processed device data can be transmitted to a central database or cloud platform through Internet of Things technology. The wireless transmission technologies that can be used include: Wi-Fi: suitable for the interior of factories or warehouses; cellular networks: suitable for devices with geographically dispersed locations; LPWAN technologies (such as LoRa, Sigfox): suitable for long-distance and low-power transmission; Bluetooth: suitable for short-distance communication.

[0025] In one embodiment, the attributes of the device data include: temperature, specifically referring to the ambient temperature during device operation, in degrees Celsius; vibration frequency, specifically referring to the vibration frequency during device operation, in Hertz; pressure, specifically referring to the pressure value during device operation, in Pascals; current, specifically referring to the amount of current used by the device, in Amperes; voltage, specifically referring to the voltage value used by the device, in Volts; operating duration, specifically referring to the operating time of the device from startup to the data acquisition moment, in hours; fault code, specifically referring to the error code recorded when the device fails; maintenance record, specifically referring to the time of the last maintenance of the device; production batch, specifically referring to the production batch number of the device; model, specifically referring to the model identification of the device.

[0026] It should be noted that this embodiment is only to illustrate a device data format and type of the present invention. In practical applications, the attributes of the data are usually more than 10 attributes, and the number of data attributes may reach dozens or even hundreds.

[0027] Step S104, use a pre-trained neural network to perform chaotic randomization feature extraction on the operating state data to determine the target features of the operating state data.

[0028] Among them, in the embodiment of the present invention, by introducing chaos initialization into the neural network, chaotic sequences (such as Logistic mapping, Henon mapping, etc.) are used to initialize the weights or parameters of the neural network. Chaotic sequences are highly sensitive to initial conditions and have pseudo-random properties. This characteristic helps to break through the limitations of local optimal solutions and increase the possibility of exploring different solutions. In addition, using a neural network constructed by self-organizing feedback for feature extraction, the effective cooperation between the neurons of the neural network can help the network better learn the internal structure in the data and can more accurately capture the dynamic changes and non-linear relationships in the data.

[0029] Step S106, input the target features into a preset fault diagnosis model to determine the fault classification result corresponding to the target features.

[0030] The embodiment of the present invention uses a preset fault diagnosis model for fault diagnosis and classification. Among them, the fault diagnosis model adopted in the embodiment of the present invention. Step S108, determine the fault state of the device to be tested based on the fault classification result.

[0031] Through the fault diagnosis model, the target features are classified and recognized, and the probability distribution belonging to each category is output, and the category with a higher probability is determined from it to obtain the device fault state classification result indicated by the target features. Among them, it includes "normal operation" and "fault state", a total of 2 categories.

[0032] A device fault diagnosis method based on sensor data provided by an embodiment of the present invention can break through the limitation of local optimal solutions, effectively identify the internal structure of data, more accurately capture the dynamic changes and non-linear relationships in the data, and thus obtain more accurate target features. It can also make full use of the distribution characteristics of the feature space of the data, adapt to the characteristics of different data sets or changes in the device state for fault identification, and improve the effect of fault identification.

[0033] Further, an embodiment of the present invention also provides another device fault diagnosis method based on sensor data to illustrate the above step S104. Figure 2 The flowchart of the embodiment of the present invention is shown. Refer to Figure 2 , including the following steps: Step S202, obtain the operation state data of the device to be tested.

[0034] Step S204, input the operation state data into a preset neural network, and based on the oscillation state of the neurons of the neural network, perform chaotic random search on the operation state data to determine the neuron output corresponding to each neuron of the neural network.

[0035] In the prior art, the output of a neuron is usually based on the linear weighted result of the input data, and the final value is output after being processed by an activation function. Such as traditional models like multi-layer perceptrons, convolutional neural networks, etc. Among them, when the neural network processes complex problems such as device fault diagnosis, the neurons have self-dynamic adjustment and non-linear perturbations. The behavior of these neurons in the prior art mainly depends on the weighted sum of the inputs, and does not fully consider the dynamic influence of the corresponding "oscillation state" of the neurons on the output of the neural network, resulting in a weak global search ability of the network, being difficult to fully capture the dynamic changes and non-linear features of the input data, and being prone to falling into local optima, resulting in the extracted features lacking the ability to represent the abnormal behavior of the device.

[0036] In this regard, the embodiments of the present invention determine the final target features based on the self-organizing feedback of the neurons corresponding to the neural network. The target features are determined through the collaborative optimization among the neurons inside the neural network, which can enhance the global exploration ability, accelerate the convergence speed, more effectively jump out of local extrema, and approach the global optimal solution in a shorter time. Further, the embodiments of the present invention simulate the nonlinear dynamic behavior in the chaotic system, set preset oscillation parameters (such as oscillation frequency and amplitude) for the neurons. The changes in the oscillation frequency and amplitude simulate the nonlinear characteristics of many systems in nature, such as climate change, ecosystem, etc. These systems exhibit high dynamicity and complexity under certain conditions, with irregular and unpredictable characteristics. By introducing dynamic changes similar to chaotic oscillations, the neural network can enhance the exploration ability during the training process, avoid falling into local optimal solutions, and thus improve the search ability. The chaotic oscillations make the state of the neurons not only depend on the linear weighted sum of the input signals, but also be affected by their inherent nonlinear dynamic behavior, combined with the oscillation state of the current neuron, to form a dynamic correction of the output. By setting dynamic oscillation frequency and amplitude, each neuron of the neural network can generate nonlinear perturbations during the training process, which helps to capture complex patterns in the input data. Moreover, the real-time changes of the features (such as environmental temperature fluctuations or abnormal vibration frequencies) can be dynamically coupled with the chaotic oscillation state of the neurons, and the neurons can effectively cooperate, fully utilizing the internal correlation between device features to analyze complex fault patterns and improve the search ability of the neural network when extracting features.

[0037] Specifically, the oscillation parameters of the neurons of the neural network are set through the following steps: 1) Use a preset chaotic function to perform chaotic random initialization on the initial weights and biases of the neural network.

[0038] To prevent the occurrence of symmetric solutions and provide a larger search space for the neural network, first, the parameters of the neural network are initialized by performing chaotic randomization on the initial weights and biases of the neural network. The embodiments of the present invention use a chaotic function (such as a sine function or a cosine function) to perturb the initial weights, so that the initialized weights and biases of each neuron have a certain non-linear deviation. Based on this, even the originally symmetric weights will have their symmetry broken by the chaotic perturbation. Specifically, the chaotic random initialization of the initial weights and biases of the neural network is expressed as:

[0039]

[0040] In the formula, is the initial weight of the neural network, is the initial bias of the neural network, is the oscillation phase, is the first initialization angle parameter, is the second initialization angle parameter, is the fourth initialization angle parameter, is the constant offset, is the small perturbation term. Preferably, = 0.5, = 0.5, = 0.1, = 0.01, , .

[0041] Among them, the first initialization angle parameter is used to control the oscillation phase of the neuron, prevent the initial state of the neuron from being too symmetric, and enhance the exploration ability of the network. During the training process of the neural network, each neuron oscillates according to this initial phase, affecting the activation state of the neuron. If the initial phases of all neurons are the same, it may lead to symmetric solutions and then fall into local optimal solutions. By adopting different initialization angles, it is ensured that neurons have high exploration and diversity during the training process. For example, in device data, if neurons have the same initialization state for responses to features such as temperature and pressure, it may lead to a single process for extracting fault features of different devices. By initializing different angles, it is equivalent to giving each neuron a "unique starting point", so that it can better adapt to complex dynamic data changes.

[0042] The second initialization angle parameter is used to control the oscillation frequency of the neuron and adjust the response speed of the neuron to the input signal. By adjusting the second initialization angle parameter, the response range of each neuron can be controlled, making it have a stronger response in specific data patterns. For example, in device monitoring data, some sensors (such as temperature sensors) may have relatively stable responses, while other sensors (such as vibration sensors) may show more variations. Adopting the second initialization angle parameter can ensure that the responses of neurons are adaptable to different data features (such as temperature fluctuations or vibration frequency changes).

[0043] The fourth initialization angle parameter is used to control the oscillation amplitude of the neuron, affect the activation intensity of the neuron output, and ensure that the neuron can adapt to the variation amplitude of different features in the device data. In device data, the variation amplitudes of features (such as vibration frequency, temperature, etc.) may vary greatly. By initializing the fourth initialization angle parameter, the neuron can make adaptive adjustments according to the different amplitudes of these features, ensuring that the network can handle data changes of different scales. For example, if the temperature change range of the device is small while the vibration frequency change range is large, the initialization value of the fourth initialization angle parameter can adjust the response intensity of the neuron when processing different features, thereby improving the accuracy of device fault diagnosis.

[0044] 2) Set the initial oscillation frequency and amplitude for the neurons of the neural network based on the oscillation phase and the preset oscillation control parameters.

[0045] A common problem in neural network training is that the network is prone to falling into local optimal solutions. Especially in complex equipment fault diagnosis tasks, the non-linear characteristics of the data make it easy for the model to find some local but not truly globally optimal solutions. To solve this problem, the present invention adopts the chaotic effect. During the training process of the neurons, the chaotic effect, through the way of non-linear oscillation, enables each neuron to explore at different speeds and in different ways in each iteration cycle. The change in the oscillation frequency makes the state of the neuron not repeat in each iteration, but maintain a constantly changing dynamic state, thereby increasing the breadth and depth of global search and being able to better avoid local optimal solutions. Specifically, in combination with the above-mentioned oscillation phase, set the initial oscillation frequency and amplitude for each neuron, which are used to generate the chaotic effect and bring dynamic search ability during the subsequent training process. The calculation methods of the initial oscillation frequency and amplitude are expressed as:

[0046]

[0047] In the formula, is the initial oscillation frequency of the neuron, is the initial oscillation amplitude of the neuron, is the first oscillation control parameter, is the second oscillation control parameter. Preferably, = 2, = 0.1.

[0048] 3) Input the preset training sample set into the neural network to adaptively adjust the initial oscillation frequency and amplitude; and, iterate the preset oscillation phase and angle parameters based on the chaotic perturbation term corresponding to the oscillation phase.

[0049] Among them, in order to enhance the exploration ability during the neural network parameter optimization process, the embodiments of the present invention also adaptively adjust the frequency and amplitude of the chaotic oscillation to cope with the situation where abnormal values appear in the operating state data of the equipment (such as vibration frequency or current). After the oscillation amplitude and frequency are adaptively adjusted, the search and exploration ability of the neural network can be increased. Specifically, the calculation method of the adaptive adjustment of the oscillation parameters is expressed as:

[0050]

[0051] In the formula, is the neuron at the The oscillation amplitude at the $t$-th iteration, is the oscillation amplitude of the neuron at the $(t + 1)$-th iteration, is the oscillation frequency of the neuron at the $t$-th iteration, is the oscillation frequency of the neuron at the $(t + 1)$-th iteration; is the second initialization angle parameter of the neuron at the $t$-th iteration, which is updated according to the gradient descent method during the training process; is the second oscillation control parameter of the neuron at the $t$-th iteration, which is updated according to the gradient descent method during the training process. is the loss function of the neural network at the $t$-th iteration.

[0052] Among them, in the oscillation frequency update formula, the form of the exponential function is adopted, which can suppress the rapid growth of the frequency. The reciprocal of the exponential function is a function that decreases rapidly, and it is used to suppress the oscillation frequency according to the loss function. When the loss function is small, the value of will be large, so that the amplitude of frequency update is small, which helps to prevent the oscillation frequency of the neuron from fluctuating too violently. For example, in the task of equipment fault diagnosis, if the temperature of the equipment changes greatly (resulting in high loss), the frequency will be updated faster so that the network can quickly adjust to adapt to the new data; while when the equipment data changes relatively smoothly (low loss), the speed of frequency update will slow down, thus avoiding over-adjustment and keeping the network stable.

[0053] The sine function is adopted in the oscillation amplitude update formula. By introducing periodic changes, the oscillation amplitude changes periodically with the loss value during the training process. The oscillation amplitude may increase (be positive) in some stages, while it may decrease (be negative) in other stages. This periodic adjustment helps the neural network to dynamically adjust the oscillation amplitude at different training stages. For example, in the equipment monitoring data, there may be periodic fluctuations during the operation of the equipment, such as periodic changes in vibration frequency or temperature (e.g., the working cycle of mechanical equipment). The sine function can enable the neural network to make adaptive adjustments in these periodic changes, so that the neural network can better capture these periodic features and at the same time cope with occasional changes.

[0054] In summary, by using the reciprocal of a monotonically decreasing exponential function to slow down the growth rate of the frequency, as the loss decreases, the frequency update becomes more stable, which is suitable for gradually stabilizing the controlled frequency and can effectively prevent over-adjustment in high-loss and unstable data patterns. By introducing periodic fluctuations using the sine function, the change in amplitude has periodicity and volatility, which helps to dynamically adjust the response of neurons to different data patterns and is suitable for capturing periodic or fluctuating characteristics existing in device data. The combined use of the two provides the neural network with flexibility in a dynamic data environment, enabling it to more effectively extract complex features from device data and make predictions.

[0055] Among them, the loss function can be constructed based on the difference between the label obtained by performing a preset Softmax calculation on the current neural network output and the true label, which is used to measure the fitting accuracy of the neural network and update the parameters. The calculation method of the loss function is expressed as:

[0056] In the formula, is the loss function at the t-th iteration of the neural network, is the number of samples input to the neural network in the current batch; is the true label of the i-th sample. For example, the label categories include "normal operation" and "fault status", which are represented by 0 and 1 respectively; is the label obtained by performing a preset Softmax calculation on the output of the neural network for the i-th sample, is the first oscillation control parameter of the neuron at the t-th iteration.

[0057] Furthermore, in the embodiments of the present invention, the oscillation state of the neuron is changed through non-linear perturbation, avoiding being trapped in a local optimal solution during the training process and enhancing the dynamic search ability of the neural network. In the embodiments of the present invention, based on the update rule of the neuron in each iteration, the oscillation phase and angle parameters are dynamically iterated, thereby dynamically iterating the oscillation state of the neuron to generate non-linear perturbation in the time series. The calculation method of the oscillation phase iteration of each neuron is expressed as:

[0058]

[0059] In the formula, is the oscillation phase of the neuron at the t-th iteration, is the first initialization angle parameter of the neuron at the t-th iteration, is the first initialization angle parameter of the neuron at the (t - 1)-th iteration, is the oscillation phase of the neuron at the (t - 1)-th iteration, is the oscillation frequency of the neuron at the t-th iteration, is the preset time step, is the chaotic perturbation term of the neuron at the t-th iteration, which is used to generate a non-linear random effect at each iteration. Preferably, Δt = 0.01.

[0060] Among them, in the embodiment of the present invention, the chaotic perturbation term is calculated by non-linearly mapping the oscillation phase, the first oscillation control parameter, and the second initialization angle parameter. The first oscillation control parameter is used to control the initial growth rate of the neuron oscillation frequency, which determines the speed at which the neuron responds to the input data during training. It affects how the neuron adjusts its frequency under different input features and data changes, and thus affects the dynamic behavior of the neuron. The second initialization angle parameter is used to control the initial phase angle of the oscillation to ensure that the oscillation of the neuron has a certain initial state at the beginning of training. By adjusting these two parameters in the embodiment of the present invention, the neural network can respond more flexibly to different data patterns, avoid falling into local optimal solutions, and enhance its adaptability and search ability in a dynamic environment. Specifically, the calculation method of the chaotic perturbation term is expressed as:

[0061] In the formula, is the perturbation coefficient, is the first oscillation control parameter of the neuron at the (t - 1)-th iteration, is the oscillation phase of the neuron at the (t - 1)-th iteration, is the second initialization angle parameter of the neuron at the (t - 1)-th iteration. Preferably, = 0.05.

[0062] Combined with the above update process, the embodiment of the present invention also updates the weight parameters of the neural network, and the update method is expressed as:

[0063] In the formula, is the weight of the neural network at the (t + 1)-th iteration, is the weight of the neural network at the -th iteration, is the adjustment amount of the weight of the neural network based on error backpropagation at the -th iteration, is the chaotic perturbation term of the neuron at the -th iteration.

[0064] Furthermore, the calculation method of the adjustment amount of the weight of the neural network based on error backpropagation is expressed as:

[0065] In the formula, is the learning rate of the neural network at the t-th iteration, is the partial derivative of the loss with respect to the weights of the neural network at the t-th iteration. Preferably, = 0.01.

[0066] Furthermore, the bias of the neural network is updated in the same way, expressed as:

[0067] In the formula, is the bias of the neural network at the (t + 1)-th iteration, is the bias of the neural network at the t-th iteration, is the adjustment amount of the bias of the neural network at the t-th iteration based on error backpropagation.

[0068] Furthermore, the calculation method of the adjustment amount of the bias of the neural network based on error backpropagation is expressed as:

[0069] In the formula, is the partial derivative of the loss with respect to the bias of the neural network at the t-th iteration.

[0070] 4) Until the neural network meets the preset training requirements, the final oscillation parameters of the neurons are obtained.

[0071] In summary, during the training process, by introducing nonlinear perturbations, as the oscillation phase and frequency change, the state of the neurons changes continuously over time, avoiding fixed patterns, enhancing the exploration ability of the network, and responding to fluctuations in device data, such as data on temperature changes, abnormal vibration frequencies, etc. The oscillatory state enables the neurons to adapt to dynamic changes in the input data. In addition, the oscillatory state also characterizes the interaction between neurons. Especially when there are internal connections between neurons, the oscillatory state can effectively capture this relationship. For example, in the data of multiple sensors of a device, the oscillatory state can help the network identify the dynamic coupling relationship between features such as temperature and vibration frequency, pressure, etc.

[0072] Step S206: Determine the self-organizing feedback amount corresponding to the neural network according to the neuron output of each neuron.

[0073] Step S208: Adjust the neuron output according to the self-organizing feedback amount to determine the target features of the operating state data.

[0074] In summary, the complex and unpredictable dynamic behavior (i.e., the oscillatory state) generated by the oscillation and chaotic effects of neurons during the training process in the embodiments of the present invention reflects their response intensity and change trend to the input data. By adjusting the oscillation frequency and amplitude, the output of each neuron is not only related to the linear weighted result of the data features of the input device, but also combined with the oscillatory state of the current neuron to form a dynamic correction of the output. When the features in the device data (such as temperature, vibration, etc.) fluctuate, the oscillatory state can automatically adjust the activation output of the neuron, making it more sensitive to these fluctuations, so as to more accurately capture the abnormal state of the device. Based on this, when extracting features from the device data, the real-time changes of the features (such as environmental temperature fluctuations or abnormal vibration frequencies) are dynamically coupled with the chaotic oscillatory state, facilitating the capture of the dynamic changes and non-linear features of the data and improving the search ability of the neural network. Correspondingly, the calculation method of the output activation function of each neuron is expressed as:

[0075] In the formula, is the activation output of the neuron in the neural network, is the weight of the neuron in the neural network at the t-th iteration, is the bias of the neuron in the neural network at the t-th iteration; is the data feature of the input device received by the neuron in the neural network. For example, the feature attributes include: temperature, specifically referring to the environmental temperature during device operation, in degrees Celsius; vibration frequency, specifically referring to the vibration frequency during device operation, in Hertz; pressure, specifically referring to the pressure value during device operation, in Pascals; current, specifically referring to the current consumption of the device, in Amperes; voltage, specifically referring to the voltage value used by the device, in Volts; operation duration, specifically referring to the operation time of the device from startup to the data acquisition moment, in hours; fault code, specifically referring to the error code recorded when the device fails; maintenance record, specifically referring to the time of the last maintenance of the device; production batch, specifically referring to the production batch number of the device; model, specifically referring to the model identifier of the device. Each feature attribute may exhibit different change patterns during the operation of the device, and the embodiments of the present invention can help the neural network better capture these changes based on the current oscillatory state by adjusting the oscillation frequency and amplitude of the neuron. is the oscillation amplitude of the neuron at the t-th iteration, is the current iteration number, is a factor for adjusting the oscillation influence. Preferably, =0.3. Based on this, when the features in the device data change (such as temperature fluctuations or abnormal vibration frequencies), the oscillation state can dynamically couple the input features, automatically adjust the output of the neurons, enabling the neural network to adapt to the changes in the device state, and timely correct errors during the training process, dynamically modify the output, and improve the accuracy and robustness of the model.

[0076] In addition, the output of each neuron reflects the changes in their states, and the differences in these output states determine the feedback strength between neurons. The output of each neuron in the embodiments of the present invention is not only related to its own input signal but also related to the states of adjacent neurons. Through self-organizing feedback for the collaborative adjustment of the neural network, each neuron in the neural network adjusts its output and input weights through internal local feedback and the cooperation of adjacent neurons, enabling the network to adaptively optimize its structure and tend towards an optimal configuration. Based on this, when the neural network extracts features from device data, between neurons with similar device data features (such as temperature and vibration frequency may have an inherent association), the feedback weight coefficient can be used as a factor to adjust the feedback strength, control the strength and importance of the feedback, affect the degree of cooperation between neurons, and achieve collaborative optimization, which can better capture the cross information of device data. The calculation method of the self-organizing feedback amount is expressed as:

[0077] In the formula, is the feedback amount between the current neuron and the q-th neuron, is the feedback weight coefficient between the current neuron and the q-th neuron, is the output of the current neuron, is the output of the q-th neuron. Preferably, =0.2. Further, the weights of the neural network can be adjusted based on the self-organizing feedback amount to adjust the neuron output. In specific implementation, the update method of the neural network weight parameters implemented in the present invention is expressed as:

[0078] is the feedback amount between the current neuron and the q-th neuron, represents the summation of the feedback amounts of all adjacent neurons of the current neuron, represents all adjacent neurons of the current neuron.

[0079] In summary, the embodiments of the present invention can introduce dynamic and irregular response patterns for the neurons of the neural network through a chaotic oscillator to prevent the network from falling into local optimal solutions during the training process. And at the beginning of network training, chaotic random initialization is performed, and unpredictability is introduced by randomizing the initial parameters of the neurons (such as weights and biases), thereby expanding the search space and avoiding symmetric solutions. Further, during the training process, the dynamic behavior of the neurons is controlled by the set oscillation parameters (such as oscillation frequency and amplitude), so that they show non-linear changes in the time series, thereby enhancing the adaptability and search ability of the neural network to data. The embodiments of the present invention are based on the combined action of a chaotic oscillator, random initialization, and oscillation frequency and amplitude settings to ensure that the neurons can capture complex patterns in the data through complex dynamic adjustments during the training process.

[0080] Regarding the neural network proposed in this application, by analyzing the influence of different parameter initialization methods on the model training process, comparing the convergence trends of chaotic random initialization with traditional random initialization and standard parameter initialization methods, the advantages of this technology in search space construction are verified. Refer to Figure 3 , which shows a schematic diagram of the influence of different initialization methods on the training loss. Based on Figure 3 The experimental results shown indicate that the model processed by chaotic randomization can quickly enter the optimization track at the beginning of training, and the convergence process is more stable, indicating that chaotic perturbation breaks the parameter symmetry, provides a more reasonable initial search direction for the neural network, effectively avoids the local optimal stagnation problem caused by unreasonable initial parameter distribution in traditional methods, and significantly shortens the training cycle required for the model to reach the best performance.

[0081] Furthermore, analyze the stability performance in a noise interference environment. By injecting Gaussian noise with different intensities into the test data, compare the anti-interference capabilities of this technology with methods such as standard neural networks, dropout regularization, and weight decay regularization. Figure 4 shows a schematic diagram of the performance comparison of different algorithms under noisy data. Refer to Figure 4 The experimental results shown indicate that as the noise intensity increases, the performance degradation of this technology is significantly less than that of other methods. Its dynamic oscillation mechanism enables the network to spontaneously filter out abnormal signals through non-linear perturbation, adaptively adjust the feature extraction strategy, and maintain a stable decision boundary in a complex noise environment, showing stronger environmental adaptability.

[0082] Step S210: Input the target feature into a preset fault diagnosis model to determine the fault classification result corresponding to the target feature.

[0083] The device data after feature extraction is input into a preset fault diagnosis model for classification, such as support vector machine, extreme learning machine, random forest, decision tree, Softmax function, etc., to obtain the categories of device fault diagnosis, such as including "normal operation" and "fault state", a total of 2 categories.

[0084] Step S212, determine the fault state of the device to be tested based on the fault classification result.

[0085] In summary, another device fault diagnosis method based on sensor data provided by the embodiments of the present invention searches for operation state data based on the preset oscillation frequency and amplitude of neurons in the neural network, and uses the coupling of the neuron oscillation state and the dynamic change of features to extract features, which can improve the ability to capture the non-linear features of device data and improve the feature extraction effect in a complex device operation environment. Moreover, by self-organizing and feedback-adjusting the neuron output, and using the interaction between neurons to more accurately capture the internal relationship between device data features, the effectiveness of feature extraction is improved. In addition, the weight initialization of the neural network is performed in a chaotic randomization manner, and the oscillation frequency and amplitude are set for neurons by using an oscillation mechanism, which can avoid falling into local optimum, enhance the global search ability of the neural network, and effectively improve the accuracy and efficiency of device state monitoring and fault diagnosis.

[0086] Further, on the basis of the above embodiments, the embodiments of the present invention also provide another device fault diagnosis method based on sensor data. The embodiments of the present invention mainly describe the training sample set used. Figure 5 shows a flowchart of a method for constructing a training sample set provided by an embodiment of the present invention. Refer to Figure 5 and the method includes the following steps: Step S10, obtain the pre-collected device operation monitoring data.

[0087] Step S12, according to the device operation state indicated by the device operation monitoring data, perform data annotation on the device operation monitoring data to construct an initial sample set.

[0088] Among them, the device operation monitoring data can refer to the operation state data of the above embodiments and will not be elaborated here. Further, the collected device data is annotated to construct an initial sample set. In one embodiment, the annotation method of the present invention is manual annotation, and the annotated categories include "normal operation" and "fault state", a total of 2 categories.

[0089] It can be understood that the acquisition, annotation, and preprocessing of device data are time-consuming and labor-intensive, and insufficient training samples are likely to lead to poor generalization ability of the model, and at the same time affect the accuracy of the model. In the process of expanding device data in the prior art, a fixed selection method is usually adopted to determine the samples to be expanded. However, due to the complex distribution of device data, the prior art cannot adapt to the characteristics of complex data distribution, resulting in insufficient diversity of generated samples and a decrease in the accuracy of the classification model when dealing with device anomalies.

[0090] In order to adapt to the data characteristics, the embodiments of the present invention adopt a dynamic selection method for data expansion, dynamically adjusting the selection range of samples to be expanded according to the feature distribution of each sample point, making the sample generation more diverse and more adaptable.

[0091] Specifically, refer to the following steps S14 - S20.

[0092] Step S14, determine the feature distribution of the initial sample set.

[0093] The overall statistical characteristics and structure of all samples in the dataset in the feature space. The embodiments of the present invention perform data expansion based on the feature distribution, which can generate diverse and adaptable samples, enhancing the generalization ability of the model for device data with complex distributions. In specific implementation, the embodiments of the present invention eliminate the feature scale differences through standardization to ensure that the distance calculation (such as Euclidean distance) in the feature space can accurately reflect the true form of the data distribution. Then, according to dynamic neighborhood selection, the neighborhood range is dynamically adjusted according to the density of samples in the feature space (such as sparse or aggregated) to adapt to complex data distributions. Among them, samples have relative positions and densities in the feature space. By calculating information such as the distance, density, inter-class and intra-class distributions between sample points, the feature distribution of sample points can be comprehensively understood. Further, the embodiments of the present invention calculate the feature standard deviation of the initial sample set based on the feature mean of the initial sample set, and perform feature space normalization processing on the initial sample set to ensure that the expanded samples generated according to the current feature distribution are close to the actual device data distribution, avoiding the decrease in training effect caused by feature scale differences.

[0094] Among them, the calculation method of the feature standard deviation of the original device data is expressed as:

[0095] In the formula, is the total number of samples, is the feature value of the i-th original device data.

[0096] Perform feature space normalization processing on the collected original device data to ensure that the generated synthetic samples are closer to the distribution of actual device data, avoiding affecting the training effect of the model due to inconsistent feature scales, which is expressed as:

[0097] In the formula, is the normalized device data; is the original device data; is the characteristic mean value of the original device data, is the characteristic standard deviation of the original device data.

[0098] Step S16: Determine the target position to be augmented from the initial sample set based on the feature distribution.

[0099] In specific implementation, the embodiment of the present invention determines the sample augmentation weight of the minority-class samples corresponding to the initial sample set based on the feature distribution; and determines the target position to be augmented corresponding to each sample according to the sample augmentation weight and the Euclidean distance between each sample in the initial sample set. The feature distribution includes the distribution and quantity of samples of different classes. The embodiment of the present invention mainly performs data augmentation on the minority-class samples. The minority-class samples usually cannot cover the complete feature distribution space. For example, for a characteristic value (current value) of equipment failure data, the failure interval is [10A, 50A]. If there is less failure data, such as only 3 pieces of failure data, and the current values of these three pieces of failure data are set to 12A, 20A, and 25A respectively, it is obvious that the failure interval ([10A, 50A]) cannot be divided based on these three pieces of failure data. If it is augmented to 1000 pieces, the current values corresponding to these 1000 pieces of data may be spread over the interval [10A, 50A], then the corresponding failure interval can be well divided.

[0100] In specific implementation, the embodiment of the present invention uses a dynamic distance threshold (instead of a fixed number of K nearest neighbors) to calculate the Euclidean distance between each minority-class sample and all other samples, and then screens out the set of neighboring samples that meet the conditions according to the preset dynamic distance threshold. In addition, it also preferentially selects high-weight samples for interpolation in combination with the sample weights calculated based on the reliability score.

[0101] According to the distribution of each category in the original device data, calculate the weights of the minority-class samples. Samples with higher weights will be preferentially considered in subsequent sample generation. The weights in the embodiment of the present invention are set based on the reliability score of the samples to emphasize the contribution of high-quality device data samples. The calculation method is expressed as:

[0102] In the formula, is the weight of the i-th sample; is the reliability score of the i-th sample, which is obtained by calculating the class probability of the current sample through a preset Softmax classification function; is the weight adjustment threshold; is a normalization parameter. Preferably, is set to 0.2.

[0103] For each minority-class sample, the samples to be augmented are dynamically selected according to the distribution of its feature space. The present invention adopts a dynamic proximity selection mechanism, which dynamically adjusts the selection range of the target augmentation position of each sample according to the feature distribution of the samples, and can better reflect the diversity of device data. In view of the complex distribution of device data, the representativeness and adaptability of the generated samples are improved. In the embodiment of the present invention, through an iterative process, the selection of the target augmentation position of each sample may be updated each time to adapt to the diversity of device data. The method of dynamically selecting the target augmentation position of each sample is expressed as:

[0104] In the formula, represents the set of target augmentation positions of the i-th sample; is the Euclidean distance calculation function; is the distance threshold; is the th normalized device data; is the th normalized device data; represents the th object that meets the condition, and , is the set condition. Preferably, is set to 0.5.

[0105] Step S18, data augmentation is performed on the target augmentation position through a preset sample augmentation algorithm to obtain augmented samples.

[0106] Step S20, the augmented samples and the initial sample set are combined to construct a training sample set.

[0107] In one implementation manner, data interpolation may be performed on the augmentation position based on the sample augmentation weight to generate the augmented sample corresponding to the current sample. For example, the SMOTE algorithm is combined with the dynamic proximity selection mechanism to dynamically adjust the selection range of neighboring samples according to the feature distribution of each sample point, and solve the problem that the selection of neighboring samples in the traditional SMOTE algorithm is static and the sample generation is insufficient in diversification and adaptability.

[0108] According to the SMOTE algorithm, interpolation is performed between the selected minority-class samples and their neighboring samples to generate new synthetic samples. The method of synthesizing new samples is expressed as:

[0109] In the formula, is the newly generated device data sample; is the interpolation coefficient.

[0110] Among them, the interpolation coefficient can be set by random generation to ensure the diversity of the generated samples, while avoiding the concentration of the generated device data samples in certain specific regions, improving the diversity and robustness of the data, expressed as:

[0111] In the formula, represents being subject to a specific distribution, represents a uniform distribution on the interval [0, 1].

[0112] Furthermore, the generated new samples are integrated with the original device data set to form an expanded device data set. In one embodiment, assume that the original collected device data samples are 800, and the device data expansion model expands and generates 200 samples. Then the expanded device data set contains 1000 samples.

[0113] Another device fault diagnosis method based on sensor data provided by the embodiments of the present invention can dynamically adjust the selection range of the target position to be expanded according to the characteristic distribution of the device data through a dynamic proximity selection mechanism, so as to be able to generate samples with diversity and adaptability, enhancing the generalization ability of the model for device complex distribution data. Among them, combined with feature normalization processing, it can ensure that the generated samples are close to the actual device data distribution, avoiding the decline of the training effect caused by feature scale differences. Further, weights are also assigned based on the reliability scores of minority class samples to preferentially generate high-quality samples and improve the credibility of the generated data.

[0114] Furthermore, based on the above embodiments, the embodiments of the present invention also provide a device fault diagnosis device based on sensor data, Figure 6 shows a schematic structural diagram of a device fault diagnosis device based on sensor data provided by the embodiments of the present invention. Referring to Figure 6 , the device includes: a data acquisition module 100 for acquiring the operating state data of the device to be measured; a data processing module 200 for performing chaotic randomization feature extraction on the operating state data by using a pre-trained neural network to determine the target features of the operating state data; an execution module 300 for inputting the target features into a preset fault diagnosis model to determine the fault classification result corresponding to the target features; and an output module 400 for determining the fault state of the device to be measured based on the fault classification result.

[0115] For a device fault diagnosis device based on sensor data provided by the embodiments of the present invention, its implementation principle and the technical effects generated are the same as those of the foregoing method embodiments. For a brief description, for the parts not mentioned in the device embodiment, reference can be made to the corresponding content in the foregoing method embodiments.

[0116] The above data processing module 200 is also used to input the operating state data into a preset neural network, perform chaotic random search on the operating state data based on the oscillation state of the neurons in the neural network, and determine the neuron output corresponding to each neuron in the neural network; determine the self-organizing feedback amount corresponding to the neural network according to the neuron output of each neuron; adjust the neuron output according to the self-organizing feedback amount to determine the target features of the operating state data.

[0117] The above data processing module 200 is also used to obtain the oscillation parameters of the neurons in the neural network, perform chaotic random search on the operating state data based on the oscillation parameters, and determine the neuron output corresponding to the neural network.

[0118] The above data processing module 200 is also used to perform chaotic random initialization on the initial weights and biases of the neural network by using a preset chaotic function; wherein, the chaotic function includes preset oscillation phase and angle parameters; set the initial oscillation frequency and amplitude for the neurons in the neural network based on the oscillation phase and a preset oscillation control parameter; input a preset training sample set into the neural network to adaptively adjust the initial oscillation frequency and amplitude; and iterate the preset oscillation phase and angle parameters based on the chaotic perturbation term corresponding to the oscillation phase; until the neural network meets the preset training requirements to obtain the final oscillation parameters of the neurons.

[0119] The above data processing module 200 is also used to update the weight parameters of the neural network based on the self-organizing feedback amount to adjust the neuron output.

[0120] The device further includes a construction module, which is used to obtain the pre-collected device operation monitoring data; perform data annotation on the device operation monitoring data according to the device operation state indicated by the device operation monitoring data to construct an initial sample set; determine the feature distribution of the initial sample set; determine the target position to be augmented from the initial sample set based on the feature distribution; perform data augmentation on the target position to be augmented through a preset sample augmentation algorithm to obtain augmented samples; and combine the augmented samples and the initial sample set to construct a training sample set.

[0121] The above construction module is also used to determine the sample augmentation weight of the minority class samples corresponding to the initial sample set based on the feature distribution; determine the target position to be augmented corresponding to each sample according to the sample augmentation weight and the Euclidean distance between each sample in the initial sample set.

[0122] The above construction module is also used to perform data augmentation on the target position to be augmented through a preset sample augmentation algorithm to obtain augmented samples, and the steps include: performing data interpolation on the position to be augmented based on the sample augmentation weight to generate the augmented sample corresponding to the current sample.

[0123] The above building block is also used to determine the feature mean of the initial sample set, calculate the feature standard deviation of the initial sample set based on the feature mean, and perform feature space normalization processing on the initial sample set based on the feature standard deviation to determine the feature distribution of the initial sample set.

[0124] An embodiment of the present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the steps of any of the above Figures 1 to 5 shown methods are implemented. An embodiment of the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is run by a processor, the steps of the above Figures 1 to 5 shown methods are executed. An embodiment of the present invention also provides a schematic structural diagram of an electronic device, as Figure 7 shown, which is the schematic structural diagram of the electronic device. Among them, the electronic device includes a processor 61 and a memory 60. The memory 60 stores computer-executable instructions that can be executed by the processor 61. The processor 61 executes the computer-executable instructions to implement the above Figures 1 to 5 shown method. In Figure 7 the shown embodiment, the electronic device further includes a bus 62 and a communication interface 63. Among them, the processor 61, the communication interface 63, and the memory 60 are connected through the bus 62.

[0125] Among them, the memory 60 may include high-speed random access memory (RAM), and may also include non-volatile memory, such as at least one disk memory. The communication connection between this system network element and at least one other network element is realized through at least one communication interface 63 (which can be wired or wireless), and the Internet, wide area network, local area network, metropolitan area network, etc. can be used. The bus 62 can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, an EISA (Extended Industry Standard Architecture) bus, etc., and can also be an AMBA (Advanced Microcontroller Bus Architecture) bus. Among them, AMBA defines three types of buses, including the APB (Advanced Peripheral Bus) bus, the AHB (Advanced High-performance Bus) bus, and the AXI (Advanced eXtensible Interface) bus. The bus 62 can be divided into an address bus, a data bus, a control bus, etc. For the sake of convenience of representation, Figure 7 only a two-way arrow is used in Figure 7 to represent it, but it does not mean that there is only one bus or one type of bus.

[0126] The processor 61 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by the integrated logic circuit of the hardware in the processor 61 or the instructions in the form of software. The above-mentioned processor 61 may be a general-purpose processor, including a central processing unit (CPU for short), a network processor (NP for short), etc.; it may also be a digital signal processor (DSP for short), an application specific integrated circuit (ASIC for short), a field-programmable gate array (FPGA for short) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as being executed and completed by the hardware decoding processor, or executed and completed by the combination of the hardware and software modules in the decoding processor. The software module may be located in a mature storage medium in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. This storage medium is located in the memory, and the processor 61 reads the information in the memory and combines its hardware to complete the foregoing Figures 1 to 5 any of the illustrated methods.

[0127] A computer program product of a device fault diagnosis method and device based on sensor data provided by an embodiment of the present invention includes a computer-readable storage medium storing program code. The instructions included in the program code can be used to execute the method described in the foregoing method embodiment. For specific implementation, reference can be made to the method embodiment and will not be elaborated herein. Those skilled in the art can clearly understand that for the convenience and brevity of description, the specific working process of the above-described system can refer to the corresponding process in the foregoing method embodiment and will not be elaborated herein. Additionally, in the description of the embodiments of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "coupled" shall be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be directly connected or indirectly connected through an intermediate medium, and it can be the communication inside two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances. If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in various embodiments of the present invention. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), magnetic disks, or optical discs that can store program code.

[0128] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings. It is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation to the present invention. In addition, the terms "first", "second", "third" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance. Finally, it should be noted that the above embodiments are only specific embodiments of the present invention, which are used to illustrate the technical solutions of the present invention rather than to limit them. The protection scope of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art within the technical scope disclosed by the present invention can still modify the technical solutions recorded in the foregoing embodiments or can easily conceive of changes, or make equivalent replacements for some of the technical features; and these modifications, changes or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered by the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.

Claims

1. A device fault diagnosis method based on sensor data, characterized in that: The method comprises: Obtain the operating status data of the device under test; Using a pre-trained neural network to perform chaotic randomization feature extraction on the operating status data to determine target features of the operating status data; wherein the neural network is constructed based on self-organizing feedback; Inputting the target feature into a preset fault diagnosis model to determine a fault classification result corresponding to the target feature; The fault status of the device under test is determined based on the fault classification result.

2. The method according to claim 1, characterized in that The step of extracting chaotic random features from the operating status data using a pre-trained neural network to determine target features of the operating status data comprises: Inputting the running state data into a preset neural network, performing a chaotic random search on the running state data based on the oscillation state of neurons of the neural network, and determining a neuron output corresponding to each neuron of the neural network; Determining a self-organizing feedback amount corresponding to the neural network according to the neuron output of each neuron; According to the self-organizing feedback amount, the neuron output is adjusted to determine the target characteristics of the operating status data.

3. The method according to claim 2, characterized in that The step of inputting the running state data into a preset neural network, performing a chaotic random search on the running state data based on the oscillation state of neurons of the neural network, and determining the neuron output corresponding to each neuron of the neural network comprises: The oscillation parameters of the neurons of the neural network are obtained, and based on the oscillation state of the neurons corresponding to the oscillation parameters, a chaotic random search is performed on the operation state data to determine the neuron output corresponding to the neural network.

4. The method according to claim 3, characterized in that The method for calculating the oscillation parameters of the neuron comprises: Using a preset chaotic function, the initial weights and biases of the neural network are randomly initialized; wherein the chaotic function includes preset oscillation phase and angle parameters; Based on the oscillation phase and preset oscillation control parameters, setting an initial oscillation frequency and amplitude for neurons of the neural network; Inputting a preset training sample set into the neural network, adaptively adjusting the initial oscillation frequency and amplitude; and iterating the preset oscillation phase and angle parameters based on the chaotic disturbance term corresponding to the oscillation phase; Until the neural network meets the preset training requirements, the final oscillation parameters of the neuron are obtained.

5. The method according to claim 2, characterized in that: The step of adjusting the neuron output according to the self-organizing feedback amount to determine the target feature of the operating state data includes: Based on the self-organizing feedback amount, the weight parameters of the neural network are updated to adjust the neuron output.

6. The method according to claim 1, characterized in that The method for constructing a preset training sample set includes: Obtain pre-collected equipment operation monitoring data; According to the equipment operation status indicated by the equipment operation monitoring data, data annotation is performed on the equipment operation monitoring data to construct an initial sample set; Determining the characteristic distribution of the initial sample set; Based on the feature distribution, determining a target position to be expanded from the initial sample set; Performing data expansion on the target location to be expanded using a preset sample expansion algorithm to obtain an expanded sample; The expanded samples and the initial sample set are combined to construct a training sample set.

7. The method according to claim 6, characterized in that The step of determining a target expansion position from the initial sample set based on the feature distribution includes: Based on the feature distribution, determining the sample expansion weights of the minority class samples corresponding to the initial sample set; According to the sample expansion weight and the Euclidean distance between each sample in the initial sample set, the target position to be expanded corresponding to each sample is determined.

8. The method according to claim 7, characterized in that The step of performing data expansion on the target position to be expanded by using a preset sample expansion algorithm to obtain an expanded sample includes: Data interpolation is performed on the position to be expanded based on the sample expansion weight to generate an expanded sample corresponding to the current sample.

9. The method according to claim 6, characterized in that The step of determining the characteristic distribution of the initial sample set comprises: Determine a characteristic mean of the initial sample set, and calculate a characteristic standard deviation of the initial sample set based on the characteristic mean; Based on the feature standard deviation, feature space normalization processing is performed on the initial sample set to determine the feature distribution of the initial sample set.

10. A device for diagnosing equipment faults based on sensor data, characterized in that: The device comprises: A data acquisition module is used to obtain the operating status data of the device under test; A data processing module, used to perform chaotic randomization feature extraction on the operating status data using a pre-trained neural network to determine target features of the operating status data; wherein the neural network is constructed based on self-organizing feedback; An execution module, used for inputting the target feature into a preset fault diagnosis model to determine a fault classification result corresponding to the target feature; An output module is used to determine the fault status of the device under test based on the fault classification result.

Images