Equipment comprehensive efficiency evaluation method and device based on industrial interconnection
By building feature extraction models and autoencoders in industrial interconnection environments, combined with the dynamic adjustment strategy of extreme learning machines, the difficulty of efficiency evaluation of traditional methods in high-dimensional and complex data environments is solved, and higher data adaptability and Prediction accuracy.
Patent Information
- Application Number
- CN202411405059.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-10
- Publication Date
- 2024-11-08
- Estimated Expiration
- 2044-10-10
AI Technical Summary
Traditional equipment efficiency evaluation methods cannot fully capture the complex data relationships in the operation of industrial equipment, and lack flexibility and accuracy, especially in high-dimensional and complex distribution data environments, which are difficult to effectively analyze and feature extraction.
Using an industrial interconnection-based method, the neural network parameters are optimized by constructing a feature extraction model, using the layer depth distribution pressure value of neurons and simulating internal stress of the crust, combined with the autoencoder and the limit learning machine, the network structure and classification threshold are dynamically adjusted to Extract the target characteristics and efficiency levels during the operation of the equipment.
Improve the adaptability and accuracy of high-dimensional and complex distributed data, enhance the learning efficiency and prediction accuracy in dynamic data environments, improve the flexibility and robustness of classification, and can quickly respond to data distribution changes and noise. .
Smart Images

Figure CN118917555A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data processing technology, and in particular to a method and device for evaluating comprehensive equipment efficiency based on industrial interconnection. Background Art
[0002] With the continuous improvement of industrial automation and intelligence, higher requirements are placed on the operating efficiency and maintenance management of industrial equipment. Traditional equipment efficiency evaluation methods usually rely on manual monitoring or simple automation systems. These methods often fail to fully capture the complex data relationships in equipment operation and lack flexibility and accuracy in data processing and efficiency evaluation. In addition, due to the diversity of industrial equipment types and operating environments, equipment data presents high-dimensional and complex distribution characteristics, making effective data analysis and feature extraction more difficult. Summary of the invention
[0003] In view of this, the purpose of the present invention is to provide a method and device for evaluating the comprehensive efficiency of equipment based on industrial interconnection, which can comprehensively capture the complex data relationships in equipment operation and improve the flexibility and accuracy of classification.
[0004] In a first aspect, an embodiment of the present invention provides a method for evaluating the comprehensive efficiency of equipment based on industrial interconnection, wherein the method includes: obtaining equipment operating parameters of industrial equipment; extracting target features in the equipment operating parameters through a pre-constructed feature extraction model; wherein neurons of the feature extraction model are assigned pressure values based on layer depth, and the neural network parameters are optimized by simulating the internal stress of the earth's crust; the layer depth is used to characterize the number of layers of neurons; inputting the target features into a preset autoencoder, adjusting the network layer connection method of the autoencoder based on the data flow changes of the target features, and capturing the key low-dimensional representations in the target features; inputting the key low-dimensional representations into a preset extreme learning machine for preliminary prediction, and adjusting the classification threshold of the extreme learning machine based on the results of the preliminary prediction; classifying the key low-dimensional representations based on the adjusted classification threshold to determine the efficiency level of the industrial equipment.
[0005] In combination with the first aspect, an embodiment of the present invention also provides a first implementation method of the first aspect, wherein the target feature is input into a preset autoencoder, and based on the data flow change of the target feature, the step of adjusting the network layer connection mode of the autoencoder includes: inputting the target feature into the preset autoencoder, encoding it through the multi-layer neural network of the autoencoder; dynamically reconstructing the topology of each layer of the neural network of the autoencoder through an adaptive activation function, and adjusting the connection structure of the network layer of the autoencoder.
[0006] In combination with the first aspect, an embodiment of the present invention also provides a second implementation of the first aspect, wherein the above method also includes: training a preset autoencoder through a preset training sample set, and calculating the reconstruction error corresponding to the training sample set; calculating the loss function of the autoencoder based on the reconstruction error and a preset regularization term; and updating the parameters of the autoencoder using the loss function and the gradient descent method.
[0007] In combination with the first aspect, an embodiment of the present invention also provides a third implementation of the first aspect, wherein the step of adjusting the classification threshold of the extreme learning machine based on the result of the preliminary prediction includes: comparing the result of the preliminary prediction with the predicted output to determine the error size; based on the error size and the variance of the error size, calculating a new classification threshold to adjust the classification threshold of the extreme learning machine.
[0008] In combination with the first aspect, an embodiment of the present invention also provides a fourth implementation of the first aspect, wherein the above method also includes: performing classification training on a preset extreme learning machine through a preset training sample set; performing a gradient accumulation operation during the training process of the extreme learning machine, and updating the parameters of the extreme learning machine based on the accumulated gradient.
[0009] In combination with the first aspect, an embodiment of the present invention also provides a fifth implementation of the first aspect, wherein a method for constructing a feature extraction model includes: obtaining a preset training sample set and a feature extraction neural network; assigning a pressure value to each layer of neurons based on a layer depth parameter of each layer of neurons in the feature extraction neural network; training the feature extraction neural network through the training sample set, and calculating an adjustment value of the pressure value based on a loss function value of the feature extraction neural network; optimizing the neural network parameters of the feature extraction neural network based on the adjustment value until the feature extraction neural network meets preset requirements, thereby constructing a feature extraction model.
[0010] In combination with the first aspect, an embodiment of the present invention further provides a sixth implementation of the first aspect, wherein the above method also includes: calculating a pressure adjustment factor of the neuron based on the activity of the neuron; and updating the parameters of the feature extraction neural network based on the pressure adjustment factor and the adjustment value.
[0011] In combination with the first aspect, an embodiment of the present invention further provides a seventh implementation method of the first aspect, wherein the above method also includes: obtaining pre-collected equipment operating parameter samples; mapping the equipment operating parameter samples to a high-dimensional kernel space, and based on the sample categories of the equipment operating parameter samples, performing sample expansion on the equipment operating parameter samples to generate expanded samples; merging the expanded samples and the equipment operating parameter samples to construct a training sample set.
[0012] In combination with the first aspect, an embodiment of the present invention further provides an eighth implementation of the first aspect, wherein the device operation parameter samples are mapped to a high-dimensional kernel space, and based on the sample categories of the device operation parameter samples, the device operation parameter samples are expanded to generate expanded samples, including: mapping the device operation parameter samples to the high-dimensional kernel space through a kernel function; in the high-dimensional kernel space, identifying the majority class samples among the k nearest neighbors of the minority class samples of the device operation parameters, and determining the generation sample area; interpolating the generation sample area to generate synthetic samples; and using an inverse mapping function to inversely map the synthetic samples back to the original feature space to generate expanded samples.
[0013] In the second aspect, an embodiment of the present invention provides an equipment comprehensive efficiency evaluation device based on industrial interconnection, wherein the device includes: a parameter acquisition module, used to obtain equipment operating parameters of industrial equipment; a feature extraction module, used to extract target features in the equipment operating parameters through a pre-built feature extraction model; wherein the neurons of the feature extraction model are assigned pressure values based on the layer depth, and the neural network parameters are optimized by simulating the internal stress of the earth's crust; the layer depth is used to characterize the number of layers of neurons; a data processing module, used to input the target features into a preset autoencoder, adjust the network layer connection method of the autoencoder based on the data flow changes of the target features, and capture the key low-dimensional representations in the target features; an execution module, used to input the key low-dimensional representations into a preset extreme learning machine for preliminary prediction, and adjust the classification threshold of the extreme learning machine based on the results of the preliminary prediction; an output module, used to classify the key low-dimensional representations based on the adjusted classification threshold, and determine the efficiency level of the industrial equipment.
[0014] The embodiments of the present invention bring the following beneficial effects: The embodiments of the present invention provide a method and device for evaluating the comprehensive efficiency of equipment based on industrial interconnection. By integrating the principles of geomechanics into the neural network design, the model can understand and learn data in a manner similar to the crustal structure, thereby improving the model's adaptability and accuracy to high-dimensional and complexly distributed equipment operating parameters. The dynamic structural adjustment capability of the encoder ensures that the model can more effectively extract target features according to changes in the data stream, enhancing learning efficiency and prediction accuracy in a dynamic data environment. Combining the rapid prediction capability of the extreme learning machine (ELM) with the dynamic classification threshold adjustment strategy, a rapid response to changes in data distribution is achieved, the flexibility and robustness of classification are improved, and the model can still maintain high performance in the face of data distribution offset or noise.
[0015] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention are realized and obtained by the structures particularly pointed out in the description, claims and drawings.
[0016] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, preferred embodiments are given below and described in detail with reference to the accompanying drawings. BRIEF DESCRIPTION OF THE DRAWINGS
[0017] In order to more clearly illustrate the specific implementation methods of the present invention or the technical solutions in the prior art, the drawings required for use in the specific implementation methods or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some implementation methods of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.
[0018] Figure 1 A flowchart of a method for evaluating comprehensive equipment efficiency based on industrial interconnection provided by an embodiment of the present invention; Figure 2 A flowchart of another method for evaluating comprehensive equipment efficiency based on industrial interconnection provided by an embodiment of the present invention; Figure 3 A flowchart of a method for constructing a training sample set provided by an embodiment of the present invention; Figure 4 A schematic diagram of the structure of an equipment comprehensive efficiency evaluation device based on industrial interconnection provided by an embodiment of the present invention; Figure 5 A schematic diagram of the structure of another device for evaluating comprehensive efficiency of equipment based on industrial interconnection provided by an embodiment of the present invention; Figure 6 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION
[0019] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution of the present invention will be clearly and completely described in combination with the embodiments below. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0020] The embodiments of the present invention provide a method and device for evaluating comprehensive equipment efficiency based on industrial interconnection, which can comprehensively capture the complex data relationships in equipment operation and improve the flexibility and accuracy of classification.
[0021] To facilitate understanding of this embodiment, firstly, a method for evaluating comprehensive efficiency of equipment based on industrial interconnection disclosed in an embodiment of the present invention is described. Figure 1 A flowchart of a method for evaluating comprehensive equipment efficiency based on industrial interconnection provided by an embodiment of the present invention is shown. Figure 1 As shown, the method comprises the following steps: Step S102, obtaining equipment operating parameters of industrial equipment.
[0022] Step S104: extracting target features from the equipment operating parameters using a pre-built feature extraction model.
[0023] In specific implementation, in order to effectively evaluate the equipment efficiency, the embodiment of the present invention performs data processing on the equipment operation parameters of industrial equipment. First, the target features in the equipment operation parameters are extracted through a pre-built feature extraction model. In order to solve the problem that the prior art is difficult to effectively analyze high-dimensional and complexly distributed data, and the feature extraction of this type of data is difficult, the neurons of the feature extraction model of the embodiment of the present invention are assigned pressure values based on the layer depth, and the neural network parameters are optimized by simulating the internal stress of the crust. At different depths of the network, neurons are assigned weights or activation thresholds that reflect geological pressure. Simulating the law of pressure changes with depth in nature can enable the model to adjust its parameters in a similar way to the crust structure, and thus better understand and learn data. The pressure value of the neuron can be adjusted dynamically to ensure that the network can better simulate the geomechanical processes in the real world, so as to be able to process high-dimensional and complexly distributed data and achieve more efficient and more practical feature representation.
[0024] The data of the embodiment of the present invention is collected from the operating parameters of various industrial equipment. The corresponding equipment operating parameters are monitored in real time by sensors and collected through the industrial Internet platform. The collected data is stored in a structured manner, specifically in JSON format.
[0025] In one embodiment, the attributes of the data include: a1 refers to the equipment operation time (hours); a2 refers to the energy consumption (kWh); a3 refers to the equipment load ratio (%); a4 refers to the temperature (degrees Celsius); a5 refers to the vibration frequency (Hz); a6 refers to the noise level (dB); a7 refers to the number of maintenance times (times / month); a8 refers to the time between failures (days); a9 refers to the output efficiency (unit / hour); a 10 Refers to the estimated life of the equipment (years). It should be noted that this embodiment is only used to illustrate a data format and type of the present invention. In actual applications, the attributes of the data are usually more than 10 attributes, and the number of attributes of the data may reach dozens or even hundreds.
[0026] Step S106, inputting the target feature into a preset autoencoder, adjusting the network layer connection mode of the autoencoder based on the data flow change of the target feature, and capturing the key low-dimensional representation of the target feature.
[0027] In order to extract the most meaningful low-dimensional representation from the data after high-dimensional feature extraction, the complexity of the data in subsequent processing is effectively reduced and the processing efficiency is improved. The embodiment of the present invention reduces the dimension of the target features through a pre-built autoencoder to capture its key low-dimensional representation. The structure of the traditional autoencoder is predefined and fixed, which may appear to be rigid when processing complex or highly variable data. The autoencoder of the embodiment of the present invention dynamically adjusts the network structure to better match the target features to adapt to changes in the data stream, which can effectively improve the efficiency and accuracy of the model in a changing data environment.
[0028] Step S108: input the key low-dimensional representation into a preset extreme learning machine for preliminary prediction, and adjust the classification threshold of the extreme learning machine based on the result of the preliminary prediction.
[0029] Step S110 , classifying the key low-dimensional representations based on the adjusted classification threshold to determine the efficiency level of the industrial equipment.
[0030] The autoencoder of the embodiment of the present invention has a stronger adaptability to different types of features, can more accurately capture the key low-dimensional representation of the target feature, reduce the encoding of irrelevant information, and improve the efficiency and quality of feature representation. The embodiment of the present invention identifies the data through a preset extreme learning machine to determine the classification result. Among them, the extreme learning machine realizes classification through the efficiency level label of the learning data. In one embodiment, the labeled categories include: low efficiency level, medium efficiency level, high efficiency level, a total of 3 categories.
[0031] Traditional extreme learning machines (ELM) usually use a fixed classification threshold, such as 0, as the decision boundary for binary classification problems. This limits its adaptability to complex decision boundaries. When data is unevenly distributed or noisy, a fixed threshold may not be sufficient to accurately distinguish samples of different categories. The embodiment of the present invention first uses an extreme learning machine to make a preliminary prediction of the data, and adjusts its classification threshold based on the prediction results. The method of dynamically adjusting the threshold can better fit the actual data distribution, provide a more flexible and robust classification strategy, and better adapt to changes in data distribution, thereby potentially improving performance on unseen data and improving the adaptability and accuracy of the model.
[0032] In summary, the embodiment of the present invention provides a method for evaluating the comprehensive efficiency of equipment based on industrial interconnection. By integrating the principles of geomechanics into the neural network design, the model can understand and learn data in a manner similar to the crustal structure, thereby improving the model's adaptability and accuracy to high-dimensional and complexly distributed industrial equipment parameters. The dynamic structural adjustment capability of the encoder ensures that the model can more effectively extract target features according to changes in the data stream, enhancing learning efficiency and prediction accuracy in a dynamic data environment. Combining the rapid prediction capability of the extreme learning machine (ELM) with the dynamic classification threshold adjustment strategy, a rapid response to changes in data distribution is achieved, and the flexibility and robustness of classification are improved, so that the model can still maintain high performance when facing data distribution offsets or noise.
[0033] Furthermore, based on the above embodiment, the embodiment of the present invention also provides another method for evaluating the comprehensive efficiency of equipment based on industrial interconnection. Figure 2 A flowchart of another method for evaluating comprehensive equipment efficiency based on industrial interconnection provided by an embodiment of the present invention is shown. Figure 2 As shown, the method comprises the following steps: Step S202, obtaining equipment operating parameters of industrial equipment.
[0034] Step S204: extracting target features from the equipment operating parameters using a pre-built feature extraction model.
[0035] In combination with the above embodiments, the embodiments of the present invention illustrate the optimization process of the neural network parameters of the feature extraction model. Among them, existing feature extraction technologies such as conventional neural networks may also encounter the problem of gradient disappearance or explosion, and are prone to fall into local optimal solutions, which limits the performance and stability of the model on complex data sets. In this regard, the present invention is inspired by the pressure distribution in geology and the deformation process of rock layers, and simulates the dynamic adjustment process of internal stress in the earth's crust to optimize the weights and bias parameters of the neural network. The present invention adopts a geological pressure simulation optimization algorithm to adjust the parameters during the neural network training process, and automatically adjusts the intensity and direction of the pressure simulation according to the feedback of the loss function to achieve more accurate parameter optimization, thereby improving training efficiency and model performance. Specifically, the method for constructing the feature extraction model of the embodiment of the present invention is as follows: 1) Obtain the preset training sample set and feature extraction neural network.
[0036] In one embodiment, the training sample set of the embodiment of the present invention corresponds to the equipment operation parameters of the industrial equipment. The feature extraction neural network used is a 3-layer fully connected neural network for feature extraction. First, the parameters of the neural network are initialized, including weights and bias In one embodiment, the initialization method is random initialization.
[0037] 2) Based on the layer depth parameters of each layer of neurons in the feature extraction neural network, a pressure value is assigned to each layer of neurons.
[0038] According to the optimization principle of geological pressure simulation, the first The initial pressure value of each neuron The initial pressure value is based on the preset layer depth parameter Distribution, the deeper the layer, the greater the initial pressure.
[0039] Among them, the geological pressure simulation optimization algorithm is used to simulate the pressure distribution in the underground rock layer and find the most suitable "mining" plan through optimization technology. This type of algorithm usually combines the principles of geomechanics, fluid mechanics and numerical simulation technology to maximize resource mining efficiency or minimize risks under given constraints (such as cost and safety factors). The initial pressure of the neuron in the embodiment of the present invention is defined as:
[0040] In the formula, is a hyperparameter for adjusting the pressure sensing depth. Preferably, Set to 5. In this embodiment, the neural network used is a 3-layer fully connected neural network, so the value of d is 3, and d1 is 1, d2 is 2, and d3 is 3.
[0041] 3) Train the feature extraction neural network through the training sample set, and calculate the adjustment value of the pressure value based on the loss function value of the feature extraction neural network.
[0042] The input data x (i.e., the training sample set) passes through the neural network and calculates the output result y of the neural network. The output result y of the neural network is calculated by the preset Softmax function. The output of the lth layer of the neural network is set to y l , calculated as:
[0043] In the formula, The neural network The input of the layer, is the Sigmoid activation function, and They are the neural network The weight matrix and bias vector of the layer.
[0044] The loss function of the neural network is calculated as:
[0045] In the formula, is the target output, that is, the true label of the sample; is the loss function of the neural network.
[0046] Furthermore, according to the value of the loss function of the current neural network, the pressure adjustment value of each layer is calculated, thereby updating the neural network parameters.
[0047] Among them, according to the gradient of the loss function , calculate the pressure adjustment value, adjust the pressure adjustment increment of each layer, the calculation method is expressed as:
[0048] In the formula, is the learning rate of the neural network, For the The pressure adjustment increment of the layer neural network. Preferably, Set to 0.3.
[0049] Furthermore, the gradient of the loss function of the neural network The calculation method is expressed as:
[0050] Substituting the above formula into the calculation formula of pressure adjustment increment, it is expressed as:
[0051] 4) Optimize the neural network parameters of the feature extraction neural network based on the adjustment values until the feature extraction neural network meets the preset requirements and construct a feature extraction model.
[0052] In order to make the model pay more attention to the part that contributes the most to the final output, the embodiment of the present invention also calculates the pressure adjustment factor of the neuron based on the activity of the neuron; based on the pressure adjustment factor and the adjustment value, the parameters of the feature extraction neural network are updated. Among them, by adopting a pressure-sensitive feedback mechanism, the influence of each neuron is dynamically adjusted based on the activity of the neuron, so that the network pays more attention to the part that contributes the most to the final output. Specifically, define Tier The activity of neurons for:
[0053] In the formula, It is Tier The net input to a neuron.
[0054] Furthermore, the pressure adjustment factor of each neuron takes into account the activity of the neuron and is calculated as:
[0055] In the formula, It is Tier The stress adjustment factor for each neuron, is the regularization coefficient of the neuron, It is The total number of neurons in the layer, No. Tier The activity of neurons. Set to 0.3.
[0056] Furthermore, according to the pressure response results of each layer, the network parameters of the corresponding layer are adjusted, and the adjustment method is expressed as:
[0057]
[0058] In the formula, Update the symbols for the parameters, is the proportional factor adjusted according to pressure, represents the element-wise product, For the The weights of the neurons in the layer, For the The bias of the neurons in the layer, For the The gradient of the weights of the neurons in the layer, For the The gradient of the bias of the layer neurons. Preferably, Set to 0.5.
[0059] The embodiment of the present invention also performs collaborative optimization on the parameters of the entire network, and transmits the pressure change effect to all relevant parameters through the back propagation mechanism to ensure the collaborative optimization of the parameters of the entire network. The calculation method of the weight gradient of the layer neuron is expressed as:
[0060] In one embodiment, let the activation function The derivative of , then the weight gradient The calculation method is expressed as:
[0061] In the formula, The neural network The transpose of the layer's input, To find the sign of the partial derivative.
[0062] Repeat the above steps until the preset stop iteration condition is met, which means that the model training is completed. In one embodiment, the preset stop iteration condition is reaching a preset maximum number of iterations. Preferably, the preset maximum number of iterations is set to 1000 times.
[0063] In summary, the embodiment of the present invention adopts a three-layer fully connected neural network, which automatically adjusts the intensity and direction of the pressure simulation according to the feedback of the loss function and combines the geological pressure simulation optimization algorithm to update the neural network parameters, thereby solving the problems of gradient disappearance or explosion and falling into the local optimal solution during the feature extraction process.
[0064] Step S206, input the target feature into a preset autoencoder, adjust the network layer connection mode of the autoencoder based on the data flow change of the target feature, and capture the key low-dimensional representation of the target feature.
[0065] The existing autoencoder technology is usually used as an unsupervised learning method, mainly used in the fields of data dimension reduction, feature learning and generative modeling. The basic structure consists of two parts: encoder and decoder. The encoder is responsible for compressing the input data into a latent representation, which often has a lower dimension; while the decoder attempts to reconstruct the original input data based on this latent representation. This process can be regarded as an operation in which the data is "encoded" by the encoder and then "decoded" by the decoder. The purpose is to make the reconstructed data as close to the original input as possible, thereby forcing the model to learn an effective representation of the data. In traditional autoencoders, the topology of the network is fixed, that is, the number of layers of the encoder and decoder, the number of neurons in each layer, and the connection method between them are defined when the model is initialized. This static structure of the autoencoder mainly relies on training algorithms (such as gradient descent) and regularization techniques (such as Dropout, L1 / L2 regularization) to optimize the network weights, thereby improving the quality of data representation.
[0066] In order to better capture the key features of industrial equipment parameters that present high-dimensional and complex distribution characteristics, the embodiment of the present invention dynamically optimizes the topological structure of the autoencoder, automatically adjusts the connection mode of the network layer according to the changes in the data flow, and can more flexibly adapt to the inherent structure of different data sets to dynamically optimize the network and more efficiently capture the key features of the data, especially when processing non-static data sets that change over time or conditions. Specifically, the target features after feature extraction are input into the improved autoencoder of the embodiment of the present invention, and encoded through the multi-layer neural network of the autoencoder; the topology of each layer of the neural network of the autoencoder is dynamically reconstructed through an adaptive activation function, and the connection structure of the network layer of the autoencoder is adjusted.
[0067] The steps to capture the key low-dimensional representation are as follows: 1) Initialize the autoencoder network parameters, including weights and biases. In one embodiment, the parameters are initialized according to a normal distribution, which is expressed as:
[0068]
[0069] In the formula, For the autoencoder Neuron to The initial weights of the neurons; For the autoencoder The initial bias of each neuron; It means that it obeys a specific distribution. represents normal distribution; is the variance of the autoencoder initialization. Preferably, Set to 0.01.
[0070] 2) In the encoding stage, the input data is encoded by a multi-layer neural network, and each layer of the network adaptively adjusts its structure through dynamic topology reconstruction, which can be expressed as:
[0071]
[0072] In the formula, It is the autoencoder The weighted input sum of the layer; For the autoencoder Tier Neuron to Tier The weights of the neurons; For the autoencoder Tier Neuron to Tier The bias of each neuron; It is the autoencoder The output of the layer; is the activation function of the autoencoder, whose input is divided by In addition, it also includes dynamically adjusted adaptive activation function parameters Preferably, The ReLU activation function calculation method is used.
[0073] In one embodiment, the adaptive activation function parameters The calculation method is:
[0074] In the formula, Represents the Sigmoid activation function; and They represent the first Layer weights and biases; Represents the first The output of the layer.
[0075] 3) At the deepest level of the encoding process, the data is compressed into a low-dimensional intermediate representation, which is the feature vector after dimensionality reduction. The calculation method is expressed as:
[0076] In the formula, is the encoded intermediate representation of the autoencoder; is the final weighted sum of the encoding layer of the autoencoder; are the specific activation parameters of the intermediate layers of the autoencoder.
[0077] 4) In the decoding phase, starting from the intermediate representation, the data is reconstructed through the decoding network layers. Each layer of the network attempts to reconstruct the original data while retaining as much key information as possible. The decoding process is expressed as:
[0078]
[0079] In the formula, Represents the decoding level of the autoencoder, which is the opposite of the encoding level; and They are the decoding layers of the autoencoder. Layer inputs and outputs; is the decoding layer of the autoencoder The output of the layer; and They represent the decoding layer of the autoencoder. Layer weights and biases; is the decoding layer of the autoencoder Layer-specific activation parameters are calculated in the same way as the encoding layer.
[0080] In summary, the embodiments of the present invention use an autoencoder to perform feature dimensionality reduction and dynamically optimize the network topology structure, automatically adjusting the connection method of the network layer according to the changes in the data flow, so that the network structure is more adaptable to the data characteristics, thereby solving the problem that the fixed network structure cannot effectively adapt to data changes.
[0081] Furthermore, the autoencoder of the embodiment of the present invention is trained by a preset training sample set, and the data after feature extraction of the training sample set using the above-mentioned feature extraction model can be used as the training sample set. The embodiment of the present invention also calculates the reconstruction error corresponding to the training sample set, calculates the loss function of the autoencoder based on the reconstruction error and the preset regularization term; and updates the parameters of the autoencoder using the loss function and the gradient descent method.
[0082] The training process combines the above steps and uses the reconstruction error and regularization term to calculate the loss function during the encoding and decoding process, optimizing the network parameters to minimize the difference between the original input and the reconstructed output. The calculation method is expressed as:
[0083] In the formula, is the loss function of the autoencoder; is the input of the autoencoder; is the reconstructed output of the autoencoder; is the regularization parameter of the autoencoder; is the L2 norm. Preferably, Set to 0.3.
[0084] Furthermore, the gradient descent method is used to update the parameters, and the loss function The calculation method of the partial derivative with respect to the weight is expressed as:
[0085] In the formula, and They are respectively The actual input of the sample and the output of the network reconstruction; The total number of samples input to the autoencoder for the current batch; is the partial derivative of the output of the autoencoder with respect to the weights, calculated by the chain rule in backpropagation.
[0086] Furthermore, in the decoding phase, the partial derivative of the output with respect to the activation input is calculated as:
[0087] In the formula, The partial derivative of the decoding layer output with respect to the activation input; is the activation function The derivative of a function with respect to its input.
[0088] Through multiple iterations of training, the network parameters are continuously adjusted. The weights and biases are updated by the gradient descent method. The update method is:
[0089]
[0090] In the formula, is the learning rate of the autoencoder; and is the gradient of the autoencoder's loss function with respect to weights and biases. Preferably, Set to 0.03.
[0091] Repeat the above steps until the preset stop iteration condition is met, which means that the model training is completed. In one embodiment, the preset stop iteration condition is reaching a preset maximum number of iterations. Preferably, the preset maximum number of iterations is set to 1000 times.
[0092] Step S208: input the key low-dimensional representation into a preset extreme learning machine for preliminary prediction.
[0093] In the forward propagation calculation process of the extreme learning machine of the embodiment of the present invention, the input dimensionality reduction features are processed by weighted sum and activation function to generate the output of the hidden layer, and then the output layer generates the prediction result. Specifically, suppose is the input feature of the extreme learning machine, that is, the feature after dimensionality reduction of the autoencoder, and calculates the output h of the hidden layer of the extreme learning machine and the prediction result of the output layer as follows:
[0094]
[0095] In the formula, and They are the weight matrices of the hidden layer and output layer of the current iteration of the extreme learning machine; and are the bias vectors of the hidden layer and output layer of the current iteration of the extreme learning machine; is the output vector of the hidden layer of the extreme learning machine; is the prediction result of the output layer of the extreme learning machine.
[0096] Step S210, comparing the preliminary prediction result with the prediction output to determine the error size; and calculating a new classification threshold based on the error size and the variance of the error size.
[0097] Traditional extreme learning machines (ELM) usually use a fixed classification threshold, such as 0, as the decision boundary for binary classification problems. Such methods often focus on using hidden layers with random weights and minimizing the weights of the output layer to achieve fast and effective learning. The classification results are directly based on the positive and negative values generated by the activation function of the output layer (such as the Sigmoid function) to determine the category.
[0098] The embodiment of the present invention compares the actual output with the predicted output, and dynamically adjusts the threshold value according to the size of the error. The embodiment of the present invention dynamically adjusts the threshold value so that the model can better adapt to the distribution of categories in the data set, especially in the case of imbalanced categories, and can effectively improve the overall classification accuracy of the model. Moreover, in the face of noisy data or data distribution that changes over time, the dynamic threshold strategy helps the model maintain stable performance and reduce misclassification. In addition, by adjusting the threshold value by considering the error and its variability, the model can learn from the training data more flexibly and improve its performance on unseen data, that is, enhance the generalization ability. The dynamic threshold strategy helps prevent the model from overfitting the noise in the training data, especially when the amount of data is limited.
[0099] If the prediction is wrong, the threshold is increased to enhance the conservatism of the model; otherwise, the threshold is decreased to increase the sensitivity of the model. is the actual output, error and the adjusted threshold The calculation method is:
[0100]
[0101] In the formula is a sign function; is the maximum value symbol; is the prediction error of the extreme learning machine; and are the thresholds of the current and next iteration of the extreme learning machine, respectively; is the learning rate of the extreme learning machine threshold adjustment; and It is the extreme learning machine’s adjustment of the threshold sensitivity and the threshold offset.
[0102] Furthermore, define and The calculation method is:
[0103]
[0104] In the formula, is the extreme learning machine scaling factor, represents the variance of the extreme learning machine error. Preferably, Set to 0.3.
[0105] In addition, the embodiment of the present invention classifies and trains the preset extreme learning machine through the preset training sample set to obtain a trained extreme learning machine. During the training process of the extreme learning machine, the embodiment of the present invention also performs a gradient accumulation operation to update the parameters of the extreme learning machine based on the accumulated gradient.
[0106] Specifically, the extreme learning machine of the present invention is an extreme learning machine based on a learnable threshold, which is used as a classifier model to identify data. Furthermore, the embodiment of the present invention also uses an adaptive gradient accumulation mechanism in the traditional extreme learning machine framework to fine-tune the weights of the hidden layer to improve the model's ability to identify abnormal data and generalization performance, which helps to stabilize the training process and avoid overfitting.
[0107] Specifically, the training process of the extreme learning machine algorithm based on the learnable threshold is as follows: a- Initialize the weight, bias and threshold parameters of the extreme learning machine. represents the initial value of the weight, represents the initial value of the bias, represents the initial value of the classification threshold. In one embodiment, and The initialization method is random initialization. The initialization value is set to 1.0.
[0108] b-In each iteration, not only the gradient of the current batch is calculated, but also the previous gradient information is accumulated, and the weights are updated with the accumulated gradient to achieve a smoother learning process. The extreme learning machine accumulates the gradient and update the weights using the accumulated gradients The calculation method is expressed as:
[0109]
[0110] In the formula, and are the accumulated gradients of the current and previous iterations of the extreme learning machine, respectively; is the momentum factor of the extreme learning machine gradient accumulation; is the loss function of the extreme learning machine under the current weight about The gradient of is the learning rate of the extreme learning machine; and are the weight matrices of the current and next iterations of the extreme learning machine, respectively. Preferably, Set to 0.3, Set to 0.01.
[0111] Further, The calculation method is expressed as:
[0112] In the formula, is the loss function of the extreme learning machine For model output The partial derivative of is the output of the extreme learning machine For weight In one embodiment, the loss function of the extreme learning machine adopts the cross entropy loss.
[0113] The accuracy of the classification results is fed back into the model training process, and the learning rate of the next round of extreme learning machine is adjusted according to the classification accuracy. The way to dynamically adjust the learning rate is expressed as:
[0114] In the formula, and are the learning rates of the current and next iterations of the extreme learning machine; is the learning rate adjustment factor of the extreme learning machine; It's about error Preferably, Set to 0.4, is the mean error of the last five iterations.
[0115] c- Repeat the above steps until the preset stop iteration condition is met, indicating that the model training is completed. In one embodiment, the preset stop iteration condition is reaching a preset maximum number of iterations, preferably, the preset maximum number of iterations is set to 1000 times.
[0116] In summary, the extreme learning machine of the embodiment of the present invention adopts a dynamically adjusted classification threshold, allowing the model to automatically adjust the classification decision boundary according to the training data, which is crucial for distinguishing normal data from abnormal data. Compared with a fixed threshold, a learnable threshold can more accurately reflect the distribution characteristics of the data and improve the recognition accuracy of abnormal points. Moreover, the embodiment of the present invention combines an adaptive gradient accumulation mechanism to train the extreme learning machine. By accumulating historical gradient information, each weight update can integrate feedback from more training instances, which helps the model learn the global features of the data rather than just fitting a single batch of data, thereby improving the performance of the model on unseen data, that is, generalization ability.
[0117] Compared with using only the instantaneous gradient, the cumulative gradient can provide a more stable gradient signal, reduce fluctuations during the training process, and help avoid drastic changes in weights caused by individual abnormal batches of data, thereby making the training process smoother and more stable. In addition, the embodiments of the present invention help the model learn more general rules rather than the details of specific samples by more extensively considering the data distribution information cumulative gradient, which helps alleviate the overfitting phenomenon, especially when the amount of data is limited.
[0118] Step S212: classify the key low-dimensional representations based on the adjusted classification threshold to determine the efficiency level of the industrial equipment.
[0119] In one implementation, the classification categories of the embodiment of the present invention include three categories: low efficiency level, medium efficiency level, and high efficiency level.
[0120] Furthermore, based on the above embodiments, the embodiments of the present invention also designs a training sample set. Specifically, the embodiments of the present invention also provide another method for evaluating the comprehensive efficiency of equipment based on industrial interconnection. This embodiment mainly describes the method for constructing a training sample set. Figure 3 A flowchart of a method for constructing a training sample set is shown, such as Figure 3 As shown, the method comprises the following steps: Step S10, obtaining pre-collected equipment operation parameter samples.
[0121] The equipment operation parameter samples can refer to the equipment operation parameters of the above embodiment. When constructing the training sample set, the embodiment of the present invention also labels the collected data, and the labeling method of the present invention is manual labeling. The labeled labels refer to the above embodiment, such as low efficiency level, medium efficiency level, and high efficiency level, a total of 3 categories.
[0122] Step S11, mapping the equipment operation parameter samples to a high-dimensional kernel space, and based on the sample categories of the equipment operation parameter samples, performing sample expansion on the equipment operation parameter samples to generate expanded samples.
[0123] It is understandable that in the task of the present invention, the collection, acquisition, labeling and preprocessing of training data are time-consuming and labor-intensive, and insufficient training samples can easily lead to poor generalization ability of the model and affect the accuracy of the model. In this regard, the embodiment of the present invention also performs data expansion on the samples. In the specific implementation, the present invention maps the equipment operation parameter samples to a high-dimensional kernel space through a kernel function; The embodiment of the present invention identifies the majority class samples in the k nearest neighbors of the minority class samples of the equipment operation parameters in the high-dimensional kernel space, determines the generated sample area, interpolates the generated sample area to generate synthetic samples, and uses the inverse mapping function to inversely map the synthetic samples back to the original feature space to generate expanded samples. Among them, the embodiment of the present invention performs data expansion on the minority class samples.
[0124] In the specific implementation, by using a kernel function-based method to calculate the similarity between samples, complex nonlinear relationships can be captured during data expansion to more accurately simulate the real data distribution, thereby determining the samples to be expanded. The type of kernel function and its parameters are set. In one embodiment, the kernel function is set to a Gaussian kernel function, and the calculation method is expressed as:
[0125] In the formula, and Respectively data samples and data samples; is the width parameter of the Gaussian kernel function; Represents the distance metric function in the kernel space after Gaussian kernel transformation.
[0126] In this embodiment, the calculation method of the width parameter of the kernel function is expressed as:
[0127] In the formula, The number of samples to interpolate for the current batch.
[0128] The original data is mapped to the high-dimensional kernel space through the kernel function. The mapping method is expressed as:
[0129] In the formula, is the mapping function, is the original data point; is the center point of the kernel function; is the mapping ratio.
[0130] In one embodiment, the mapping ratio is calculated as follows:
[0131] Furthermore, the embodiment of the present invention also determines the area where synthetic samples need to be generated based on the number of sample categories of the target category sample, such as the majority class samples in the k nearest neighbors, so as to determine the samples in the area as the samples to be expanded. In the kernel space, for each minority class sample, the majority class samples in its k nearest neighbors are identified to determine the area where synthetic samples need to be generated. Samples , the way to calculate the boundary distance is expressed as:
[0132] In the formula, and are samples x in the kernel space. i and x j The value of the kth feature; w k is the feature weight; is a weighted distance metric used to identify boundary samples.
[0133] Furthermore, the feature weight The calculation method is expressed as:
[0134] in, It is The standard deviation of the feature, The calculation method is:
[0135] In the formula, is the mean of the kth feature.
[0136] Traditional data augmentation methods, such as the SMOTE algorithm, usually generate new synthetic samples by relying on simple interpolation between minority class samples, which cannot effectively handle complex or nonlinear data distributions, limiting the model's ability to handle complex data scenarios. The embodiment of the present invention uses a kernel function-based method to calculate the similarity between samples and capture complex nonlinear relationships. It also uses the SMOTE algorithm based on inversion-guided learning for sample generation. By determining the samples to be augmented in the kernel space and inversely mapping the data from the high-dimensional kernel space to the feature space of the samples after the original feature extraction, it can retain the useful information of the generated samples in the high-dimensional space, while ensuring that these samples are still meaningful in the original feature space, which helps the model learn a more natural data distribution.
[0137] Among them, the traditional SMOTE algorithm operates directly in the original feature space and obtains synthetic samples through linear interpolation between minority class samples. In the kernel method, the embodiment of the present invention effectively avoids the complexity of high-dimensional calculations through kernel function calculation. The kernel technique can linearize nonlinearly separable data in high-dimensional space, so that after the samples generated in the high-dimensional space are returned to the original space, different categories can be more clearly divided, thereby improving the performance of the classifier. The embodiment of the present invention also inversely maps the generated data back to the original feature space to obtain an expanded sample. It can retain the useful information of the samples generated in the high-dimensional space while ensuring that these samples are still meaningful in the original feature space, which helps the model learn a more natural data distribution. In some complex data structures, kernel function mapping can reveal the potential structure of the data, and the new samples after inverse mapping can carry this structural information, which promotes the model to learn more complex patterns.
[0138] In the embodiment of the present invention, the samples to be expanded are interpolated to generate synthetic samples, and the specific steps are as follows: For each minority class sample point in the kernel space, a new sample is generated by interpolation according to its k nearest minority class neighbors in the kernel space. The generation method is expressed as:
[0139] In the formula, and is the minority class sample point in the selected kernel space; are randomly generated interpolation coefficients; is the newly generated sample point.
[0140] Furthermore, the calculation method of the interpolation coefficient is expressed as:
[0141] In the formula, is the interpolation ratio calculated based on the sample distance, For random generation The value between .
[0142] In one embodiment, the interpolation ratio is calculated as follows:
[0143] In the formula, is the L2 norm.
[0144] Furthermore, an inverse mapping function is used to inversely map the synthesized samples back to the original feature space to generate an expanded sample. The synthesized samples generated in the kernel space are inversely mapped back to the original feature space. The inverse mapping to the original space is expressed as:
[0145] In the formula, It is the data point that is inversely mapped back to the original feature space; Represents the inverse mapping function from kernel space to original space.
[0146] Furthermore, the inverse mapping function The calculation method is expressed as:
[0147] In the formula, The input sample is When The inverse transformation function of is the weight of the inversion map; is the number of features of the sample.
[0148] Furthermore, the weight of the inversion map is calculated as:
[0149] Step S12: merge the expanded samples and the equipment operation parameter samples to construct a training sample set.
[0150] The embodiment of the present invention uses the SMOTE algorithm based on inversion guided learning and uses the Gaussian kernel function to calculate the similarity between samples and generate new samples, allowing complex nonlinear relationships to be captured during data expansion and more accurately simulating the real data distribution, thereby solving the problem that traditional data expansion technology cannot effectively handle complex data distribution.
[0151] Furthermore, based on the above method embodiment, the embodiment of the present invention also provides a comprehensive equipment efficiency evaluation device based on industrial interconnection, Figure 4 FIG. 1 shows a schematic diagram of a device for evaluating comprehensive efficiency of equipment based on industrial interconnection provided by an embodiment of the present invention. Figure 4 As shown, the device includes: a parameter acquisition module 100, which is used to acquire equipment operation parameters of industrial equipment; a feature extraction module 200, which is used to extract target features in the equipment operation parameters through a pre-constructed feature extraction model; wherein the neurons of the feature extraction model are assigned pressure values based on the layer depth, and the neural network parameters are optimized by simulating the internal stress of the earth's crust; the layer depth is used to characterize the number of layers of neurons; a data processing module 300, which is used to input the target features into a preset autoencoder, adjust the network layer connection mode of the autoencoder based on the data flow change of the target features, and capture the key low-dimensional representation of the target features; an execution module 400, which is used to input the key low-dimensional representation into a preset extreme learning machine for preliminary prediction, and adjust the classification threshold of the extreme learning machine based on the result of the preliminary prediction; an output module 500, which is used to classify the key low-dimensional representation based on the adjusted classification threshold to determine the efficiency level of the industrial equipment.
[0152] An embodiment of the present invention provides an equipment comprehensive efficiency evaluation device based on industrial interconnection, and its implementation principle and technical effects are the same as those of the aforementioned method embodiment. For the sake of brief description, for matters not mentioned in the device embodiment, reference can be made to the corresponding contents in the aforementioned method embodiment.
[0153] Furthermore, based on the above device embodiment, the embodiment of the present invention also provides another device for evaluating comprehensive efficiency of equipment based on industrial interconnection. Figure 5 FIG. 1 shows a schematic diagram of the structure of another device for evaluating comprehensive efficiency of equipment based on industrial interconnection provided by an embodiment of the present invention. Figure 5 As shown, the above-mentioned data processing module 300 is also used to input the target features into a preset autoencoder, and encode them through the multi-layer neural network of the autoencoder; dynamically reconstruct the topology of each layer of the neural network of the autoencoder through an adaptive activation function, and adjust the connection structure of the network layer of the autoencoder.
[0154] The above-mentioned data processing module 300 is also used to train a preset autoencoder through a preset training sample set, and calculate the reconstruction error corresponding to the training sample set; calculate the loss function of the autoencoder based on the reconstruction error and the preset regularization term; and update the parameters of the autoencoder using the loss function and the gradient descent method.
[0155] The execution module 400 is also used to compare the preliminary prediction result with the prediction output to determine the error size; based on the error size and the variance of the error size, calculate a new classification threshold to adjust the classification threshold of the extreme learning machine.
[0156] The execution module 400 is also used to perform classification training on a preset extreme learning machine using a preset training sample set; perform a gradient accumulation operation during the training process of the extreme learning machine, and update the parameters of the extreme learning machine based on the accumulated gradients.
[0157] The feature extraction module 200 is also used to obtain a preset training sample set and a feature extraction neural network; assign a pressure value to each layer of neurons based on the layer depth parameters of each layer of neurons in the feature extraction neural network; train the feature extraction neural network through the training sample set, and calculate the adjustment value of the pressure value based on the loss function value of the feature extraction neural network; optimize the neural network parameters of the feature extraction neural network based on the adjustment value until the feature extraction neural network meets the preset requirements, and construct a feature extraction model.
[0158] The feature extraction module 200 is also used to calculate the pressure adjustment factor of the neuron based on the activity of the neuron; and update the parameters of the feature extraction neural network based on the pressure adjustment factor and the adjustment value.
[0159] The device also includes a construction module 600, which is used to obtain pre-collected equipment operation parameter samples; map the equipment operation parameter samples to a high-dimensional kernel space, and based on the sample categories of the equipment operation parameter samples, perform sample expansion on the equipment operation parameter samples to generate expanded samples; merge the expanded samples and the equipment operation parameter samples to construct a training sample set.
[0160] The above-mentioned construction module 600 is also used to map the device operation parameter samples to a high-dimensional kernel space through a kernel function; in the high-dimensional kernel space, identify the majority class samples among the k nearest neighbors of the minority class samples of the device operation parameters, and determine the generated sample area; interpolate the generated sample area to generate synthetic samples; and use an inverse mapping function to inversely map the synthetic samples back to the original feature space to generate expanded samples.
[0161] An embodiment of the present invention further provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the above Figures 1 to 3 The embodiment of the present invention also provides a computer-readable storage medium having a computer program stored thereon, and the computer program is executed by a processor to perform the above Figures 1 to 3 Any of the steps of the method shown.
[0162] The embodiment of the present invention also provides a schematic diagram of the structure of an electronic device, such as Figure 6 FIG. 1 is a schematic diagram of the structure of the electronic device, wherein 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, and the processor 61 executes the computer executable instructions to implement the above Figures 1 to 3 Any of the methods shown.
[0163] exist Figure 6In the illustrated embodiment, the electronic device further includes a bus 62 and a communication interface 63, wherein the processor 61, the communication interface 63 and the memory 60 are connected via the bus 62. The memory 60 may include a high-speed random access memory (RAM), and may also include a non-volatile memory, such as at least one disk memory. The communication connection between the system network element and at least one other network element is realized through at least one communication interface 63 (which may be wired or wireless), and the Internet, a wide area network, a local area network, a metropolitan area network, etc. may be used. The bus 62 may be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus, or an EISA (Extended Industry Standard Architecture) bus, etc. It may also be an AMBA (Advanced Microcontroller Bus Architecture) bus, where AMBA defines three types of buses, including an APB (Advanced Peripheral Bus) bus, an AHB (Advanced High-performance Bus) bus, and an AXI (Advanced Xtensible Interface) bus. The bus 62 may be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 6 Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.
[0164] 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 hardware integrated logic circuit in the processor 61 or the instructions in the form of software. The above processor 61 can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The general processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in the embodiment of the present invention can be directly embodied as a hardware decoding processor to be executed, or can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a mature storage medium in the field 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. The storage medium is located in the memory, and the processor 61 reads the information in the memory and completes the above in combination with its hardware. Figures 1 to 3 Any of the methods shown.
[0165] The computer program product of a method and device for evaluating the comprehensive efficiency of equipment based on industrial interconnection provided in an embodiment of the present invention includes a computer-readable storage medium storing program code, and the instructions included in the program code can be used to execute the method described in the previous method embodiment. The specific implementation can refer to the method embodiment, which will not be repeated here. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process of the system described above can refer to the corresponding process in the previous method embodiment, which will not be repeated here.
[0166] In addition, in the description of the embodiments of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected" and "connected" should 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, or it can be the internal connection of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to the 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 is essentially or the part that contributes to the prior art or the part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk and other media that can store program code.
[0167] In the description of the present invention, it should be noted that the terms: center, top, bottom, left, right, vertical, horizontal, inside, outside, etc., indicating the orientation or position relationship, are based on the orientation or position relationship shown in the drawings, and are 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, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", and "third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.
[0168] Finally, it should be noted that the above embodiments are only specific implementations 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 is described in detail with reference to the above embodiments, those skilled in the art should understand that any person skilled in the art can still modify the technical solutions recorded in the above embodiments within the technical scope disclosed by the present invention, or can easily think of changes, or make equivalent replacements for some of the technical features therein; 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 be included in the protection scope of the present invention. Therefore, the protection scope of the present invention shall be based on the protection scope of the claims.
Claims
1. A method for evaluating comprehensive equipment efficiency based on industrial interconnection, characterized in that: The method comprises: Obtain equipment operating parameters of industrial equipment; Extracting target features from the equipment operating parameters through a pre-built feature extraction model; wherein neurons of the feature extraction model are assigned pressure values based on layer depth, and neural network parameters are optimized by simulating internal stress of the earth's crust; the layer depth is used to characterize the number of layers of neurons; Inputting the target feature into a preset autoencoder, adjusting the network layer connection mode of the autoencoder based on the data flow change of the target feature, and capturing the key low-dimensional representation of the target feature; Inputting the key low-dimensional representation into a preset extreme learning machine for preliminary prediction, and adjusting the classification threshold of the extreme learning machine based on the result of the preliminary prediction; The key low-dimensional representation is classified based on the adjusted classification threshold to determine the efficiency level of the industrial equipment.
2. The method according to claim 1, characterized in that The step of inputting the target feature into a preset autoencoder and adjusting the network layer connection mode of the autoencoder based on the data flow change of the target feature includes: Inputting the target feature into a preset autoencoder and encoding it through a multi-layer neural network of the autoencoder; The topology of each layer of the neural network of the autoencoder is dynamically reconstructed through an adaptive activation function to adjust the connection structure of the network layer of the autoencoder.
3. The method according to claim 1, characterized in that The method further comprises: Training a preset autoencoder using a preset training sample set, and calculating a reconstruction error corresponding to the training sample set; Calculating a loss function of the autoencoder based on the reconstruction error and a preset regularization term; The parameters of the autoencoder are updated using the loss function and the gradient descent method.
4. The method according to claim 1, characterized in that: The step of adjusting the classification threshold of the extreme learning machine based on the result of the preliminary prediction comprises: Comparing the preliminary prediction result with the prediction output to determine the error size; Based on the error size and the variance of the error size, a new classification threshold is calculated to adjust the classification threshold of the extreme learning machine.
5. The method according to claim 1, characterized in that The method further comprises: Perform classification training on the preset extreme learning machine through the preset training sample set; A gradient accumulation operation is performed during the training process of the extreme learning machine, and the parameters of the extreme learning machine are updated based on the accumulated gradients.
6. The method according to claim 1, characterized in that The method for constructing the feature extraction model comprises: Obtain a preset training sample set and feature extraction neural network; Based on the layer depth parameter of each layer of neurons of the feature extraction neural network, assigning a pressure value to each layer of the neurons; Training the feature extraction neural network using the training sample set, and calculating the adjustment value of the pressure value based on the loss function value of the feature extraction neural network; The neural network parameters of the feature extraction neural network are optimized based on the adjustment value until the feature extraction neural network meets the preset requirements, thereby constructing a feature extraction model.
7. The method according to claim 6, characterized in that The method further comprises: Calculating a pressure adjustment factor of the neuron based on the activity of the neuron; Based on the pressure adjustment factor and the adjustment value, parameters of the feature extraction neural network are updated.
8. The method according to claim 1, characterized in that The method further comprises: Obtain pre-collected equipment operating parameter samples; Mapping the equipment operation parameter samples to a high-dimensional kernel space, and based on the sample categories of the equipment operation parameter samples, performing sample expansion on the equipment operation parameter samples to generate expanded samples; The expanded samples and the equipment operation parameter samples are combined to construct a training sample set.
9. The method according to claim 8, characterized in that The step of mapping the equipment operation parameter samples to a high-dimensional kernel space and performing sample expansion on the equipment operation parameter samples based on sample categories of the equipment operation parameter samples to generate expanded samples includes: Mapping the device operation parameter samples to a high-dimensional kernel space through a kernel function; In the high-dimensional kernel space, identifying majority class samples in the k nearest neighbors of minority class samples of the device operating parameters, and determining a sample generation region; Interpolating the generated sample area to generate a synthetic sample; The synthesized samples are inversely mapped back to the original feature space using an inverse mapping function to generate expanded samples.
10. A comprehensive equipment efficiency evaluation device based on industrial interconnection, characterized in that: The device comprises: A parameter acquisition module is used to obtain equipment operating parameters of industrial equipment; A feature extraction module, used to extract target features from the equipment operation parameters through a pre-built feature extraction model; wherein the neurons of the feature extraction model are assigned pressure values based on layer depth, and the neural network parameters are optimized by simulating the internal stress of the earth's crust; the layer depth is used to characterize the number of layers of neurons; A data processing module, used to input the target feature into a preset autoencoder, adjust the network layer connection mode of the autoencoder based on the data flow change of the target feature, and capture the key low-dimensional representation of the target feature; An execution module, configured to input the key low-dimensional representation into a preset extreme learning machine for preliminary prediction, and adjust a classification threshold of the extreme learning machine based on a result of the preliminary prediction; The output module is used to classify the key low-dimensional representation based on the adjusted classification threshold to determine the efficiency level of the industrial equipment.
Citation Information
Patent Citations
Power equipment partial discharge severity evaluation method based on extreme learning machine
CN110927535A
Emergency fire-fighting fire risk assessment and early warning method driven by AI large model
CN118095865A
Pressure pipeline electromagnetic ultrasonic detection method based on artificial intelligence
CN118129088A
Insulator quality detection method
CN118154997A
Obstacle sensing method and device, electronic equipment and storage medium
CN118277770A
Cited By
Equipment health level assessment method and device based on model driving
CN119179966A
Liquid nitrogen preservation effect evaluation method and system based on big data
CN119203791A
Prebaked anode production equipment health assessment method and device based on artificial intelligence
CN119357827A
