Plant device management method and device based on fusion gateway, terminal and medium

Abstract

The application discloses a kind of based on fusion gateway workshop equipment management method, device, terminal and medium, the method comprises: obtaining workshop equipment running information, workshop equipment log information and the environmental information, and the workshop equipment running information and workshop equipment log information are preprocessed, and joint representation information is obtained;According to the joint representation information, an abnormality recognition result is obtained by a pre-set abnormality recognition model;According to the joint representation information and abnormality recognition result, a workshop equipment health index is obtained by a pre-set multi-modal feature fusion model;According to the workshop equipment health index and the environmental information, a target optimization management strategy is obtained by a pre-set workshop equipment management optimization model.The application aims at accurately reducing the frequency of workshop equipment failure, to improve the operating efficiency of workshop equipment.

Description

Technical Field

[0001] The present application relates to the technical field of workshop equipment management, and in particular to a workshop equipment management method, device, terminal and medium based on a converged gateway. Background Art

[0002] Factory workshop equipment management refers to the process of monitoring, analyzing and optimizing the operating status, performance parameters, energy consumption and maintenance requirements of production equipment in the workshop to ensure efficient and stable operation of the equipment and maximize the satisfaction of production goals.

[0003] However, existing workshop equipment management methods have the following problems: there are many types of equipment in the workshop, and different equipment may use different communication protocols or management systems, making it difficult to achieve data interoperability between them. Data isolation makes it impossible to conduct comprehensive analysis and global optimization. At the same time, traditional methods often rely on empirical judgment or simple statistical analysis, making it difficult to deeply explore the potential value in the data. For complex equipment status assessment and fault prediction, traditional methods often seem inadequate. Summary of the Invention

[0004] The main purpose of this application is to provide a workshop equipment management method, device, terminal and medium based on a converged gateway, aiming to accurately reduce the frequency of workshop equipment failures and thereby improve the operating efficiency of workshop equipment.

[0005] To achieve the above objectives, the present application provides a workshop equipment management method based on a converged gateway, the method comprising:

[0006] Acquiring workshop equipment operation information, workshop equipment log information, and environmental information, and preprocessing the workshop equipment operation information and workshop equipment log information to obtain joint representation information, wherein the workshop equipment operation information is used to represent the real-time operation status of the workshop equipment, the workshop equipment log information is used to represent the historical operation status of the workshop equipment, and the joint representation information is used to represent the status of the workshop equipment at the time sequence, event, and image levels;

[0007] Obtaining an anomaly recognition result based on the joint representation information by using a preset anomaly recognition model;

[0008] By presetting a multimodal feature fusion model, a workshop equipment health index is obtained according to the joint characterization information and the abnormality recognition results;

[0009] By presetting a workshop equipment management optimization model, a target optimization management strategy is obtained according to the workshop equipment health index and the environmental information.

[0010] Specifically, the preprocessing of the workshop equipment operation information and the workshop equipment log information to obtain joint representation information includes:

[0011] Aligning the workshop equipment operation information and the workshop equipment log information through a timestamp synchronization algorithm to obtain synchronized timing signals, synchronized event texts, and synchronized thermal imaging images;

[0012] By presetting a multimodal embedding network model, the joint representation information is obtained according to the synchronized time series signal, the synchronized event text and the synchronized thermal imaging image.

[0013] Specifically, the joint characterization information includes a time series feature vector and a thermal imaging image, the preset abnormality recognition model includes an abnormality warning signal model and a thermal state classification model, and the abnormality recognition result includes an abnormality warning signal corresponding to the workshop equipment and a thermal state label corresponding to the workshop equipment;

[0014] The abnormality recognition result is obtained according to the joint characterization information by using the preset abnormality recognition model, including:

[0015] Obtaining the abnormal warning signal according to the time series feature vector through the abnormal warning signal model;

[0016] The thermal state label is obtained according to the thermal imaging image using the thermal state classification model.

[0017] Specifically, the abnormal warning signal model includes an encoder and a decoder, the encoder includes three LSTM layers, and the decoder includes three inverse LSTM layers;

[0018] The step of obtaining the abnormal warning signal according to the time series feature vector using the abnormal warning signal model includes:

[0019] Compressing the time series feature vector into a low-dimensional latent vector by the encoder;

[0020] Reconstructing the low-dimensional latent vector by the decoder to obtain a reconstructed time series feature vector;

[0021] If the mean square error between the reconstructed time series feature vector and the time series feature vector is greater than or equal to a preset dynamic threshold, the abnormal warning signal is obtained based on the reconstructed time series feature vector.

[0022] Specifically, the thermal state classification model includes a lightweight ViT module and a classification head;

[0023] Obtaining the thermal state label according to the thermal imaging image using the thermal state classification model includes:

[0024] Segmenting the thermal imaging image into at least one image block by the lightweight ViT module, and composing an image block sequence based on the image block;

[0025] Obtaining, by the classification head, the classification probability corresponding to the workshop equipment according to the image block sequence;

[0026] Based on the classification probability and the preset classification probability interval, a thermal state label corresponding to the workshop equipment is determined.

[0027] Specifically, the preset multimodal feature fusion model includes a CNN branch module, a BiGRU branch module and an attention fusion layer;

[0028] The preset multimodal feature fusion model is used to obtain the workshop equipment health index based on the joint characterization information and the abnormality recognition results, including:

[0029] Obtaining a first eigenvector according to the abnormal warning signal through the CNN branch module;

[0030] Obtaining a second feature vector according to the time series feature vector through the BiGRU branch module;

[0031] The workshop equipment health index is obtained through the attention fusion layer according to the first eigenvector and the second eigenvector.

[0032] Specifically, the preset workshop equipment management optimization model includes a first fully connected layer, a second fully connected layer, a third fully connected layer and a Gaussian strategy layer, the ratio of the number of neurons between the first fully connected layer, the second fully connected layer and the third fully connected layer is 1:2:4, the activation function of the Gaussian strategy layer is a Tanh function, and the target optimization management strategy includes the optimization control parameters of the workshop equipment;

[0033] The target optimization management strategy is obtained by presetting the workshop equipment management optimization model according to the workshop equipment health index and the environmental information, including:

[0034] Obtaining a first intermediate vector according to the workshop equipment health index and the environmental information through the first fully connected layer;

[0035] Obtaining a second intermediate vector according to the first intermediate vector through the second fully connected layer;

[0036] Obtaining, through the third fully connected layer, a preliminary distribution of control parameters according to the second intermediate vector;

[0037] The optimized control parameters are obtained according to the preliminary distribution of the control parameters through the Gaussian strategy layer.

[0038] To achieve the above objectives, the present application also provides a workshop equipment management device based on a fusion gateway, the device comprising:

[0039] The first unit is configured to obtain workshop equipment operation information, workshop equipment log information, and environmental information, and pre-process the workshop equipment operation information and workshop equipment log information to obtain joint representation information, wherein the workshop equipment operation information is used to represent the real-time operation status of the workshop equipment, the workshop equipment log information is used to represent the historical operation status of the workshop equipment, and the joint representation information is used to represent the status of the workshop equipment at the time sequence, event, and image levels;

[0040] The second unit is configured to obtain an anomaly recognition result based on the joint representation information by using a preset anomaly recognition model;

[0041] The third unit is configured to obtain a workshop equipment health index based on the joint characterization information and the abnormality recognition result by using a preset multimodal feature fusion model;

[0042] The fourth unit is used to obtain a target optimization management strategy according to the workshop equipment health index and the environmental information by using a preset workshop equipment management optimization model.

[0043] To achieve the above objectives, the present application also provides a terminal, comprising a memory storing a plurality of instructions; the processor loads instructions from the memory to execute the steps in any one of the methods provided in the present application.

[0044] To achieve the above objectives, the present application also provides a medium, which stores multiple instructions, and the instructions are suitable for a processor to load to execute the steps of any method provided in the present application.

[0045] The present application provides a workshop equipment management method, device, terminal and medium based on a fusion gateway, which can first obtain workshop equipment operation information, workshop equipment log information and the environmental information, and pre-process the workshop equipment operation information and workshop equipment log information to obtain joint characterization information, wherein the workshop equipment operation information is used to characterize the real-time operation status of the workshop equipment, the workshop equipment log information is used to characterize the historical operation status of the workshop equipment, and the joint characterization information is used to characterize the timing, event and image level conditions of the workshop equipment; then, through a preset abnormality recognition model, an abnormality recognition result is obtained according to the joint characterization information; then, through a preset multimodal feature fusion model, a workshop equipment health index is obtained according to the joint characterization information and the abnormality recognition result; finally, through a preset workshop equipment management optimization model, a target optimization management strategy is obtained according to the workshop equipment health index and the environmental information. By implementing the target optimization management strategy, the frequency of workshop equipment failures is ultimately accurately reduced, thereby improving the operation efficiency of the workshop equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A schematic flow chart of the method provided in the embodiment of the present application;

[0047] Figure 2 A schematic diagram of the structure of the device provided in the embodiment of the present application;

[0048] Figure 3 A schematic diagram of the structure of a terminal provided in an embodiment of the present application. DETAILED DESCRIPTION

[0049] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without making creative efforts are within the scope of protection of this application.

[0050] Existing workshop equipment management methods have the following problems: there are many types of equipment in the workshop, and different equipment may use different communication protocols or management systems, making it difficult to achieve data interoperability between them. Data isolation makes it impossible to conduct comprehensive analysis and global optimization. At the same time, traditional methods often rely on empirical judgment or simple statistical analysis, making it difficult to deeply explore the potential value in the data. For complex equipment status assessment and fault prediction, traditional methods often seem inadequate.

[0051] Therefore, the embodiments of the present application provide a workshop equipment management method, device, terminal and medium based on a fusion gateway to solve practical technical problems.

[0052] In some embodiments, the device may be integrated into an electronic device, which may be a terminal, a server, or other device.

[0053] In some embodiments, the server may also be implemented in the form of a terminal.

[0054] Among them, the server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud information library, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN (Content Delivery Network), as well as big information and artificial intelligence platforms.

[0055] The terminal may be a smartphone, tablet computer, laptop computer, desktop computer, smart speaker, smart watch, etc., but is not limited thereto. The terminal and the server may be directly or indirectly connected via wired or wireless communication, and this application does not impose any restrictions thereon.

[0056] It should be noted that the serial numbers of the following embodiments are not intended to limit the preferred order of the embodiments.

[0057] An embodiment of the present application provides a workshop equipment management method based on a fusion gateway, which is applied to a workshop equipment management system. The workshop equipment management system includes a fusion gateway and a server terminal. The fusion gateway is used to receive workshop equipment operation information, workshop equipment log information, and environmental information of the workshop where the workshop equipment is located, and is used to upload the workshop equipment operation information, workshop equipment log information, and environmental information to the server terminal.

[0058] Specifically, the fusion gateway is a device or system that plays a key role in the government and enterprise network environment, and plays an important role in the above-mentioned workshop equipment management method based on the fusion gateway. The factory workshop equipment management of the fusion gateway is a modern equipment management model. By using the fusion gateway as the core data collection and processing node, real-time monitoring, data analysis, fault prediction and optimized scheduling of the operating status of various equipment in the workshop can be achieved.

[0059] The converged gateway supports multiple communication protocols (such as Modbus, OPC UA, and MQTT), collecting heterogeneous data from multiple sources and different types of devices. After pre-processing, the data is transmitted to the server terminal via a secure protocol for further analysis.

[0060] The converged gateway can integrate PON optical modules (such as GPON ONUs) to directly connect to the operator's OLT via optical fiber, enabling high-speed fiber access. PON (Passive Optical Network), a fiber-based access technology, uses optical splitters to enable point-to-multipoint communication without the need for active equipment. Enterprise-class features are added to PON access, including security features such as intrusion prevention (IPS), URL filtering, and virus protection; intelligent routing with application- and link-based load balancing; and branch management with zero-configuration deployment and centralized monitoring.

[0061] The converged gateway can also be a multifunctional network device for enterprises and governments, providing internet access, security protection, and traffic management. Its core functions include NAT translation, firewall, VPN (IPsec / SSL), QoS, multi-WAN load balancing, and branch interconnection. Application scenarios include headquarters and branch network egress, government-specific network access, and cloud service connectivity.

[0062] The workshop equipment management system leverages big data analytics and artificial intelligence technologies (such as deep learning and reinforcement learning) to assess equipment operating status, predict potential failures, and optimize equipment scheduling strategies. The management system displays analysis results through a visual interface and allows managers to send control commands to workshop equipment via a converged gateway, creating a closed-loop feedback mechanism. This system supports adaptive adjustments in dynamic environments, meeting the needs of complex production scenarios while improving workshop equipment utilization and production efficiency.

[0063] like Figure 1 , the specific process of the method can be as follows:

[0064] S110. Obtain the workshop equipment operation information, the workshop equipment log information and the environmental information, and pre-process the workshop equipment operation information and the workshop equipment log information to obtain joint characterization information, wherein the workshop equipment operation information is used to characterize the real-time operation status of the workshop equipment, the workshop equipment log information is used to characterize the historical operation status of the workshop equipment, and the joint characterization information is used to characterize the status of the workshop equipment at the timing, event and image levels.

[0065] In some embodiments, the fusion gateway can parse different device protocols through a dynamic protocol adaptation engine (supporting Modbus, OPC UA, etc.), extract the workshop equipment operation information and workshop equipment log information of the workshop equipment, and obtain standardized data.

[0066] In some embodiments, the preprocessing of the workshop equipment operation information and the workshop equipment log information to obtain the joint representation information includes steps A1 to A2 as shown below:

[0067] A1, align the workshop equipment running information and the workshop equipment log information through a timestamp synchronization algorithm to obtain a synchronized time sequence signal, a synchronized event text, and a synchronized thermal imaging image.

[0068] A2, obtain the joint representation information according to the synchronized time sequence signal, the synchronized event text, and the synchronized thermal imaging image through a preset multi-modal embedding network model.

[0069] Specifically, the workshop equipment running information and the workshop equipment log information can be input into a multi-modal embedding network (MMEN) to output a joint representation vector (dimension configurable, such as 256 dimensions) in a unified feature space for representing time sequence-event-image, that is, the joint representation information.

[0070] S120, obtain an abnormality recognition result according to the joint representation information through a preset abnormality recognition model.

[0071] In some embodiments, the joint representation information includes a time sequence feature vector and a thermal imaging image, the preset abnormality recognition model includes an abnormality warning signal model and a thermal state classification model, and the abnormality recognition result includes an abnormality warning signal corresponding to the workshop equipment and a thermal state label corresponding to the workshop equipment.

[0072] Specifically, the step content of B1 to B2 as shown below is included in the step of obtaining an abnormality recognition result according to the joint representation information through a preset abnormality recognition model.

[0073] B1, obtain the abnormality warning signal according to the time sequence feature vector through the abnormality warning signal model.

[0074] Continuing to describe the above embodiments, the abnormality warning signal model includes an encoder and a decoder, the encoder includes three layers of LSTM layers, and the decoder includes three layers of inverse LSTM layers.

[0075] The step content of B11 to B13 as shown below is included in the step of obtaining the abnormality warning signal according to the time sequence feature vector through the abnormality warning signal model.

[0076] B11, compress the time sequence feature vector into a low-dimensional latent vector through the encoder.

[0077] B12, reconstruct the low-dimensional latent vector through the decoder to obtain a reconstructed time sequence feature vector.

[0078] B13, if the mean square error between the reconstructed time sequence feature vector and the time sequence feature vector is greater than or equal to a preset dynamic threshold, obtaining the abnormal warning signal based on the reconstructed time sequence feature vector.

[0079] In continuation of the above embodiment, the time sequence feature vector can be vibration spectrum data, which contains time sequence signal features.

[0080] The LSTM layer (Long Short-Term Memory) is a special RNN (Recurrent Neural Network) structure specially designed to solve the problem of gradient disappearance or gradient explosion that traditional RNNs are prone to when processing long sequence data. LSTM introduces a "gate mechanism" to control the flow of information, so as to effectively capture the long-term dependencies in time series.

[0081] The reverse LSTM layer is a variant of the LSTM (Long Short-Term Memory) network, mainly used for inverse modeling of time series data. Unlike the standard forward LSTM layer, the reverse LSTM layer calculates in the opposite order of the time series (from back to front), thereby capturing the inverse dependencies in the input sequence.

[0082] In some embodiments, the reverse LSTM layer is used in combination with the LSTM layer to form a bidirectional LSTM (Bidirectional LSTM). The bidirectional LSTM uses both forward and reverse information, thereby providing a more comprehensive understanding of time series data.

[0083] B2, obtaining the thermal state label based on the thermal imaging image through the thermal state classification model.

[0084] In continuation of the above embodiment, the thermal state classification model includes a lightweight ViT module and a classification head.

[0085] Specifically, the obtaining of the thermal state label based on the thermal imaging image through the thermal state classification model includes the following steps B21 to B23:

[0086] B21, dividing the thermal imaging image into at least one image block through the lightweight ViT module, and composing an image block sequence based on the image block.

[0087] B22, obtaining the classification probability corresponding to the workshop equipment based on the image block sequence through the classification head.

[0088] B23. Determine the thermal status label corresponding to the workshop equipment based on the classification probability and the preset classification probability interval.

[0089] In some embodiments, the thermal state classification model may be a MobileViT model.

[0090] The lightweight ViT module (Vision Transformer) is an improved version of the visual Transformer architecture that aims to make it more suitable for resource-constrained scenarios (such as mobile devices, edge computing, etc.) by reducing computational complexity and parameter count while maintaining high performance.

[0091] The classification head is a key module in deep learning models for completing classification tasks. Located at the end of the neural network, it maps features extracted by the network to specific class labels, thereby classifying the input data. Specifically, the classification head can be a fully connected layer, used to obtain the classification probabilities corresponding to workshop equipment. For example, thermal status labels include: normal (probability > 0.8), overheated (0.5 ≤ probability ≤ 0.8), and locally high temperature (probability < 0.5).

[0092] S130 , obtaining a workshop equipment health index based on the joint characterization information and the abnormality recognition result by using a preset multimodal feature fusion model.

[0093] Continuing with the above embodiment, the preset multimodal feature fusion model includes a CNN branch module, a BiGRU branch module and an attention fusion layer.

[0094] Specifically, the preset multimodal feature fusion model is used to obtain the workshop equipment health index according to the joint characterization information and the abnormality recognition result, including the steps S131 to S133 as shown below:

[0095] S131. Obtain a first eigenvector according to the abnormal warning signal through the CNN branch module.

[0096] S132. Obtain a second feature vector according to the time series feature vector through the BiGRU branch module.

[0097] S133. Obtain the workshop equipment health index according to the first eigenvector and the second eigenvector through the attention fusion layer.

[0098] In some embodiments, the CNN branch module maps abnormal warning signals (e.g., whether a device is experiencing vibration or temperature anomalies) into low-dimensional feature vectors, capturing spatial patterns (e.g., specific abnormal waveforms in a spectrum). The abnormal warning signal is the input binary abnormal signal (e.g., [1, 0, 1] indicates abnormalities in the first and third devices). The CNN branch module may include: an embedding layer that converts the abnormal signal into a continuous vector (e.g., [0.1, 0.3, 0.5]). A convolutional layer that extracts local features (e.g., high-frequency abnormal patterns in a spectrum) through 1D convolution.

[0099] The output of the CNN branch module, i.e., the first eigenvector (e.g., [0.2, 0.4, 0.6]), reflects the distribution pattern of abnormal signals.

[0100] Continuing with the above embodiment, the BiGRU branch module processes time series feature vectors (such as vibration spectrum and temperature curve) and extracts time-dependent features (such as equipment degradation trend).

[0101] The input of the BiGRU branch module is a time series feature vector (such as a vibration FFT with a length of 512)

[0102] The BiGRU branch module may include: a bidirectional GRU: which simultaneously captures forward and reverse temporal dependencies (such as abnormal signs before a fault and recovery trends after a fault). A fully connected layer: which compresses high-dimensional features into low-dimensional representations (such as from 256 dimensions to 64 dimensions).

[0103] The output of the BiGRU branch module is a second eigenvector (such as [0.05, 0.18, ..., 0.92]), which reflects the dynamic changes in the operating status of the device.

[0104] Continuing with the above embodiment, the attention fusion layer dynamically weights and fuses the feature vectors of CNN and BiGRU to generate a device health index (HI).

[0105] The input of the attention fusion layer includes: the first feature vector (the abnormal pattern features output by CNN) and the second feature vector (the time series features output by BiGRU).

[0106] The attention fusion layer can include: concatenating features: merging two branch features (e.g., [0.2, 0.4] + [0.05, 0.18] = [0.25, 0.58]). Attention mechanism: calculating the weights of the two features (e.g., 30% for abnormal signals and 70% for time series features). Weighted fusion: generating a comprehensive feature, which is mapped to a health index (HI∈[0,1]).

[0107] The output of the attention fusion layer is the workshop equipment health index (e.g., HI=0.76 indicates that the equipment is in good condition).

[0108] S140: Obtain a target optimization management strategy based on the workshop equipment health index and the environmental information by presetting the workshop equipment management optimization model.

[0109] Continuing with the above embodiment, the preset workshop equipment management optimization model includes a first fully connected layer, a second fully connected layer, a third fully connected layer and a Gaussian strategy layer. The ratio of the number of neurons between the first fully connected layer, the second fully connected layer and the third fully connected layer is 1:2:4. The activation function of the Gaussian strategy layer is the Tanh function, and the target optimization management strategy includes the optimization control parameters of the workshop equipment.

[0110] Specifically, the target optimization management strategy is obtained by presetting the workshop equipment management optimization model according to the workshop equipment health index and the environmental information, including the steps S141 to S144 shown below:

[0111] S141. Obtain a first intermediate vector through the first fully connected layer according to the workshop equipment health index and the environmental information.

[0112] S142. Obtain a second intermediate vector according to the first intermediate vector through the second fully connected layer.

[0113] S143. Obtain a preliminary distribution of control parameters according to the second intermediate vector through the third fully connected layer.

[0114] S144. Obtain the optimized control parameters according to the preliminary distribution of the control parameters through the Gaussian strategy layer.

[0115] Continuing with the above example, the inputs of the first fully connected layer include: workshop equipment health index (HI, range 0-1), environmental parameters (temperature and humidity, order priority, etc., input after standardization)

[0116] The structure of the first fully connected layer may include: number of neurons: assuming the input dimension is D, the output dimension is 2D (designed with a ratio of 1:2). Activation function: ReLU.

[0117] The first fully connected layer is used to extract the nonlinear feature interaction between the health index and environmental parameters (such as the coupling effect between HI and ambient temperature).

[0118] Continuing with the above example, the input of the second fully connected layer is the intermediate vector (e.g., 256-dimensional) output by the first layer. The structure of the second fully connected layer may include: Number of neurons: The second layer has twice as many neurons as the first layer (e.g., 512 neurons). Activation function: ReLU.

[0119] The second fully connected layer is used to further mine high-order features (such as the correlation between the changing trend of HI over time and energy consumption).

[0120] Continuing with the above embodiment, the input of the third fully connected layer may be an intermediate vector (e.g., 512-dimensional) output by the second layer.

[0121] The structure of the third fully connected layer may include: number of neurons: the number of neurons in the third layer is twice that of the second layer (e.g., 1024 neurons); activation function: ReLU.

[0122] The third fully connected layer is used to integrate global features and generate a preliminary distribution of control parameters (such as mean μ and variance σ).

[0123] Continuing with the above embodiment, the Gaussian strategy layer maps the preliminary distribution to Gaussian distribution parameters (μ, σ), and outputs the range through Tanh constraints (such as speed control within ±10%), and finally obtains the optimized control parameters.

[0124] For example, the optimized control parameters may include: speed optimization parameter: μ = 95% (base speed), σ = 5% (±5% fluctuation allowed). Cooling water flow: μ = 100% (base value), σ = 10% (dynamic adjustment). The target optimization management strategy is determined based on this.

[0125] In summary, this application provides a workshop equipment management method based on a fusion gateway. Through a workshop equipment management system based on a fusion gateway, the frequency of workshop equipment failures can be accurately reduced, thereby improving the operating efficiency of workshop equipment.

[0126] To better implement the above method, the present application also provides a workshop equipment management device based on a converged gateway. The device can be integrated into an electronic device, such as a terminal or a server. The terminal can be a mobile phone, tablet computer, smart Bluetooth device, laptop computer, personal computer, etc. The server can be a single server or a server cluster consisting of multiple servers.

[0127] For example, in this embodiment, the method of the embodiment of the present application will be described in detail by taking the specific integration of a workshop equipment management device based on a fusion gateway into a terminal as an example.

[0128] For example, Figure 2 As shown, the workshop equipment management device 200 based on the fusion gateway may include a first unit 201, a second unit 202, a third unit 203 and a fourth unit 204, and the device includes:

[0129] The first unit 201 is configured to obtain workshop equipment operation information, workshop equipment log information, and the environmental information, and pre-process the workshop equipment operation information and the workshop equipment log information to obtain joint representation information, wherein the workshop equipment operation information is used to represent the real-time operation status of the workshop equipment, the workshop equipment log information is used to represent the historical operation status of the workshop equipment, and the joint representation information is used to represent the status of the workshop equipment at the time sequence, event, and image levels;

[0130] The second unit 202 is configured to obtain an anomaly recognition result based on the joint representation information by using a preset anomaly recognition model;

[0131] The third unit 203 is configured to obtain a workshop equipment health index based on the joint characterization information and the abnormality recognition result by using a preset multimodal feature fusion model;

[0132] The fourth unit 204 is used to obtain a target optimization management strategy according to the workshop equipment health index and the environmental information by using a preset workshop equipment management optimization model.

[0133] In specific implementation, the above units can be implemented as independent entities, or can be arbitrarily combined to be implemented as the same or several entities. The specific implementation of the above units can be found in the previous method embodiments and will not be repeated here.

[0134] From the above, it can be seen that the embodiments of the present application can accurately reduce the frequency of workshop equipment failures, thereby improving the operating efficiency of workshop equipment.

[0135] The present application also provides an electronic device, which may be a terminal, a server, or the like. The terminal may be a mobile phone, a tablet computer, a smart Bluetooth device, a laptop computer, a personal computer, or the like; the server may be a single server or a server cluster consisting of multiple servers, or the like.

[0136] In some embodiments, the product processing device can also be integrated into multiple electronic devices. For example, the product processing device can be integrated into multiple servers, and the workshop equipment management method based on the fusion gateway of the present application is implemented by multiple servers.

[0137] In this embodiment, the electronic device of this embodiment is a terminal as an example for detailed description, for example, Figure 3 As shown, it shows a schematic diagram of the structure of the terminal 300 involved in the embodiment of the present application, specifically:

[0138] The terminal 300 may include one or more processors 301, one or more storage media 302, a power supply 303, an input module 304, and a communication module 305. Those skilled in the art will appreciate that Figure 3 The structure of the terminal 300 shown in the figure does not constitute a limitation on the terminal 300, and the terminal 300 may include more or fewer components than shown in the figure, or combine certain components, or arrange the components differently.

[0139] Processor 301 is the control center of terminal 300. It connects all components of terminal 300 using various interfaces and circuits. By running or executing software programs and / or modules stored in memory 302 and accessing information stored in memory 302, it executes various functions of terminal 300 and processes information, thereby providing overall monitoring of terminal 300. In some embodiments, processor 301 may include one or more processing cores. In some embodiments, processor 301 may integrate an application processor and a modem processor. The application processor primarily handles the operating system, user interface, and application programs, while the modem processor primarily handles wireless communications. It is understood that the modem processor may not be integrated into processor 301.

[0140] Memory 302 can be used to store software programs and modules. Processor 301 executes various functional applications and information processing by running the software programs and modules stored in memory 302. Memory 302 may primarily include a program storage area and an information storage area. The program storage area may store an operating system and at least one application required for a function (such as sound playback or image playback). The information storage area may store information generated based on the use of terminal 300. Memory 302 may also include high-speed random access memory and non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device. Accordingly, memory 302 may also include a memory controller to provide processor 301 with access to memory 302.

[0141] Terminal 300 also includes a power supply 303 for supplying power to various components. In some embodiments, power supply 303 can be logically connected to processor 301 via a power management system, thereby enabling the power management system to manage charging, discharging, and power consumption. Power supply 303 can also include one or more DC or AC power supplies, a recharging system, a power failure detection circuit, a power converter or inverter, a power status indicator, and other arbitrary components.

[0142] The terminal 300 may further include an input module 304 , which may be configured to receive input digital or character information and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function controls.

[0143] The terminal 300 may also include a communication module 305. In some embodiments, the communication module 305 may include a wireless module. The terminal 300 may use the wireless module of the communication module 305 to perform short-range wireless transmission, thereby providing the user with wireless broadband Internet access. For example, the communication module 305 may be used to help the user send and receive emails, browse web pages, and access streaming media.

[0144] Although not shown, the terminal 300 may further include a display unit, etc., which will not be described in detail here. Specifically, in this embodiment, the processor 301 in the terminal 300 will load the executable files corresponding to the processes of one or more application programs into the memory 302 according to the following instructions, and the processor 301 will run the application programs stored in the memory 302 to implement various functions as follows:

[0145] Acquiring workshop equipment operation information, workshop equipment log information, and the environmental information, and preprocessing the workshop equipment operation information and the workshop equipment log information to obtain joint representation information, wherein the workshop equipment operation information is used to represent the real-time operation status of the workshop equipment, the workshop equipment log information is used to represent the historical operation status of the workshop equipment, and the joint representation information is used to represent the status of the workshop equipment at the time sequence, event, and image levels;

[0146] Obtaining an anomaly recognition result based on the joint representation information by using a preset anomaly recognition model;

[0147] By presetting a multimodal feature fusion model, a workshop equipment health index is obtained according to the joint characterization information and the abnormality recognition results;

[0148] By presetting a workshop equipment management optimization model, a target optimization management strategy is obtained according to the workshop equipment health index and the environmental information.

[0149] From the above, it can be seen that the embodiments of the present application can accurately reduce the frequency of workshop equipment failures, thereby improving the operating efficiency of workshop equipment.

[0150] Those skilled in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be accomplished by instructions, or by controlling related hardware through instructions. The instructions may be stored in a medium and loaded and executed by a processor.

[0151] To this end, an embodiment of the present application provides a medium storing a plurality of instructions that can be loaded by a processor to execute the steps of any of the workshop equipment management methods based on a converged gateway provided in the embodiments of the present application. For example, the instructions can execute the following steps:

[0152] Acquiring workshop equipment operation information, workshop equipment log information, and the environmental information, and preprocessing the workshop equipment operation information and the workshop equipment log information to obtain joint representation information, wherein the workshop equipment operation information is used to represent the real-time operation status of the workshop equipment, the workshop equipment log information is used to represent the historical operation status of the workshop equipment, and the joint representation information is used to represent the status of the workshop equipment at the time sequence, event, and image levels;

[0153] Obtaining an anomaly recognition result based on the joint representation information by using a preset anomaly recognition model;

[0154] By presetting a multimodal feature fusion model, a workshop equipment health index is obtained according to the joint characterization information and the abnormality recognition results;

[0155] By presetting a workshop equipment management optimization model, a target optimization management strategy is obtained according to the workshop equipment health index and the environmental information.

[0156] The medium may include: Read Only Memory (ROM), Random Access Memory (RAM), a magnetic disk or an optical disk, etc.

[0157] According to one aspect of the present application, a computer program product or computer program is provided, the computer program product or computer program including computer instructions stored in a medium. A processor of a computer device reads the computer instructions from the medium and executes the computer instructions, causing the computer device to perform the methods provided in the various optional implementations provided in the above embodiments.

[0158] Since the instructions stored in the medium can execute the steps of any of the workshop equipment management methods based on the integrated gateway provided in the embodiments of the present application, the beneficial effects that can be achieved by any of the workshop equipment management methods based on the integrated gateway provided in the embodiments of the present application can be achieved. Please see the previous embodiments for details and will not be repeated here.

[0159] The above is a detailed introduction to the workshop equipment management method, device, terminal and medium based on the integrated gateway provided in the embodiment of the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, based on the ideas of the present application, there will be changes in the specific implementation methods and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

Claims

1. A workshop equipment management method based on a fusion gateway, characterized in that: The method comprises: Acquiring workshop equipment operation information, workshop equipment log information, and environmental information, and preprocessing the workshop equipment operation information and workshop equipment log information to obtain joint representation information, wherein the workshop equipment operation information is used to represent the real-time operation status of the workshop equipment, the workshop equipment log information is used to represent the historical operation status of the workshop equipment, and the joint representation information is used to represent the status of the workshop equipment at the time sequence, event, and image levels; Obtaining an abnormality recognition result based on the joint characterization information by using a preset abnormality recognition model; the joint characterization information includes a time series feature vector and a thermal imaging image; the preset abnormality recognition model includes an abnormality warning signal model and a thermal state classification model; and the abnormality recognition result includes an abnormality warning signal corresponding to the workshop equipment and a thermal state label corresponding to the workshop equipment; The abnormality recognition result is obtained according to the joint characterization information by using the preset abnormality recognition model, including: Obtaining the abnormal warning signal according to the time series feature vector through the abnormal warning signal model; Obtaining the thermal state label according to the thermal imaging image using the thermal state classification model; The abnormal warning signal model includes an encoder and a decoder, wherein the encoder includes three LSTM layers and the decoder includes three inverse LSTM layers; The step of obtaining the abnormal warning signal according to the time series feature vector using the abnormal warning signal model includes: Compressing the time series feature vector into a low-dimensional latent vector by the encoder; Reconstructing the low-dimensional latent vector by the decoder to obtain a reconstructed time series feature vector; If the mean square error between the reconstructed time series feature vector and the time series feature vector is greater than or equal to a preset dynamic threshold, then based on the reconstructed time series feature vector, the abnormal warning signal is obtained to fully understand the time series signal characteristics in the time series feature vector, wherein the time series feature vector is vibration spectrum data; By presetting a multimodal feature fusion model, a workshop equipment health index is obtained according to the joint characterization information and the abnormality recognition results; By presetting a workshop equipment management optimization model, a target optimization management strategy is obtained according to the workshop equipment health index and the environmental information; The preset workshop equipment management optimization model includes a first fully connected layer, a second fully connected layer, a third fully connected layer, and a Gaussian strategy layer. The ratio of the number of neurons in the first fully connected layer, the second fully connected layer, and the third fully connected layer is 1:2:

4. The activation function of the Gaussian strategy layer is a Tanh function. The target optimization management strategy includes the optimization control parameters of the workshop equipment. The target optimization management strategy is obtained by presetting the workshop equipment management optimization model according to the workshop equipment health index and the environmental information, including: Obtaining a first intermediate vector according to the workshop equipment health index and the environmental information through the first fully connected layer; Obtaining a second intermediate vector according to the first intermediate vector through the second fully connected layer; Obtaining, through the third fully connected layer, a preliminary distribution of control parameters according to the second intermediate vector; The optimized control parameters are obtained according to the preliminary distribution of the control parameters through the Gaussian strategy layer.

2. The method according to claim 1, wherein The preprocessing of the workshop equipment operation information and the workshop equipment log information to obtain joint representation information includes: Aligning the workshop equipment operation information and the workshop equipment log information through a timestamp synchronization algorithm to obtain synchronized timing signals, synchronized event texts, and synchronized thermal imaging images; By presetting a multimodal embedding network model, the joint representation information is obtained according to the synchronized time series signal, the synchronized event text and the synchronized thermal imaging image.

3. The method according to claim 1, wherein The thermal state classification model includes a lightweight ViT module and a classification head; Obtaining the thermal state label according to the thermal imaging image using the thermal state classification model includes: Segmenting the thermal imaging image into at least one image block by the lightweight ViT module, and composing an image block sequence based on the image block; Obtaining, by the classification head, the classification probability corresponding to the workshop equipment according to the image block sequence; Based on the classification probability and the preset classification probability interval, a thermal state label corresponding to the workshop equipment is determined.

4. The method according to claim 1, wherein The preset multimodal feature fusion model includes a CNN branch module, a BiGRU branch module and an attention fusion layer; The preset multimodal feature fusion model is used to obtain the workshop equipment health index based on the joint characterization information and the abnormality recognition results, including: Obtaining a first eigenvector according to the abnormal warning signal through the CNN branch module; Obtaining a second feature vector according to the time series feature vector through the BiGRU branch module; The workshop equipment health index is obtained through the attention fusion layer according to the first eigenvector and the second eigenvector.

5. A workshop equipment management device based on a fusion gateway, characterized in that: The device comprises: The first unit is configured to obtain workshop equipment operation information, workshop equipment log information, and environmental information, and pre-process the workshop equipment operation information and workshop equipment log information to obtain joint representation information, wherein the workshop equipment operation information is used to represent the real-time operation status of the workshop equipment, the workshop equipment log information is used to represent the historical operation status of the workshop equipment, and the joint representation information is used to represent the status of the workshop equipment at the time sequence, event, and image levels; A second unit is configured to obtain an abnormality recognition result based on the joint characterization information using a preset abnormality recognition model; the joint characterization information includes a time series feature vector and a thermal imaging image; the preset abnormality recognition model includes an abnormality warning signal model and a thermal state classification model; and the abnormality recognition result includes an abnormality warning signal corresponding to the workshop equipment and a thermal state label corresponding to the workshop equipment; The abnormality recognition result is obtained according to the joint characterization information by using the preset abnormality recognition model, including: Obtaining the abnormal warning signal according to the time series feature vector through the abnormal warning signal model; Obtaining the thermal state label according to the thermal imaging image using the thermal state classification model; The abnormal warning signal model includes an encoder and a decoder, wherein the encoder includes three LSTM layers and the decoder includes three inverse LSTM layers; The step of obtaining the abnormal warning signal according to the time series feature vector using the abnormal warning signal model includes: Compressing the time series feature vector into a low-dimensional latent vector by the encoder; Reconstructing the low-dimensional latent vector by the decoder to obtain a reconstructed time series feature vector; If the mean square error between the reconstructed time series feature vector and the time series feature vector is greater than or equal to a preset dynamic threshold, then based on the reconstructed time series feature vector, the abnormal warning signal is obtained to fully understand the time series signal characteristics in the time series feature vector, wherein the time series feature vector is vibration spectrum data; The third unit is configured to obtain a workshop equipment health index based on the joint characterization information and the abnormality recognition result by using a preset multimodal feature fusion model; a fourth unit, configured to obtain a target optimization management strategy based on the workshop equipment health index and the environmental information using a preset workshop equipment management optimization model; the preset workshop equipment management optimization model includes a first fully connected layer, a second fully connected layer, a third fully connected layer, and a Gaussian strategy layer; the ratio of the number of neurons in the first fully connected layer, the second fully connected layer, and the third fully connected layer is 1:2:4; the activation function of the Gaussian strategy layer is a Tanh function; and the target optimization management strategy includes optimized control parameters of the workshop equipment; The target optimization management strategy is obtained by presetting the workshop equipment management optimization model according to the workshop equipment health index and the environmental information, including: Obtaining a first intermediate vector according to the workshop equipment health index and the environmental information through the first fully connected layer; Obtaining a second intermediate vector according to the first intermediate vector through the second fully connected layer; Obtaining, through the third fully connected layer, a preliminary distribution of control parameters according to the second intermediate vector; The optimized control parameters are obtained according to the preliminary distribution of the control parameters through the Gaussian strategy layer.

6. A terminal, characterized in that: The method comprises a processor and a memory, wherein the memory stores a plurality of instructions; the processor loads instructions from the memory to execute the steps in the method according to any one of claims 1 to 4.

7. A medium, characterized in that The medium stores a plurality of instructions, and the instructions are suitable for being loaded by a processor to execute the steps in the method according to any one of claims 1 to 4.

Images