Fault identification method, device and equipment based on digital twinning and medium

Abstract

The invention discloses a fault identification method and device based on digital twinning, equipment and a medium. The method comprises the following steps: acquiring a target sensor data set corresponding to a target dust removal workshop and a target workshop model determined based on a digital twin technology; performing data analysis on the target sensor data set based on a target machine learning model, and determining a target sensing data set corresponding to the target dust removal workshop; performing fault prediction on the target sensing data set based on a target fault prediction model, and determining a target fault type corresponding to the target dust removal workshop; and performing fusion processing on the target sensing data set and the target fault type based on a preset knowledge base, determining a target fault recognition result corresponding to the target dust removal workshop, and performing visual display on the target fault recognition result based on the target workshop model. Through the technical scheme of the invention, the whole-process closed-loop management from data acquisition to fault identification can be realized, and the reliability and the operation and maintenance efficiency of the system are improved.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a fault identification method, apparatus, device, and medium based on digital twins. Background Technology

[0002] In tobacco processing, the collection and handling of tobacco stems is a crucial step, and its smooth operation directly affects the stability of subsequent processes and product quality. Therefore, real-time monitoring of the tobacco stem collection and handling system is essential.

[0003] Currently, the monitoring of the operational status of the stalk collection and processing system in the silk-making workshop generally adopts the traditional method of deploying a small number of local sensors at key points combined with regular manual inspections. However, while this method can acquire data from some discrete points, it lacks the systematic collection and integration of multi-dimensional information such as the pressure distribution of the dust removal pipeline network, material flow rate, and separator operating conditions. Essentially, it is a monitoring mode based on local and isolated factors. It cannot comprehensively and continuously grasp the dynamic transport and accumulation status of the stalks in the collection pipelines, cyclone separators, and storage silos, resulting in a significant lag in status perception and reducing the system's operational efficiency.

[0004] Therefore, how to achieve closed-loop management of the entire process from data acquisition to fault identification, and improve the reliability and operation and maintenance efficiency of the stubble collection and processing system, is an urgent problem to be solved. Summary of the Invention

[0005] This invention provides a fault identification method, device, equipment, and medium based on digital twins, which can solve the problems of low reliability and low operation and maintenance efficiency of the stubble collection and processing system.

[0006] According to one aspect of the present invention, a fault identification method based on digital twins is provided, comprising:

[0007] Acquire the target sensor data set and target workshop model corresponding to the target dust removal workshop; wherein, the target workshop model is determined based on digital twin technology;

[0008] Based on the target machine learning model, data analysis is performed on the target sensor data set to determine the target sensing data set corresponding to the target dust removal workshop;

[0009] Based on the target fault prediction model, fault prediction is performed on the target sensing data set to determine the target fault type corresponding to the target dust removal workshop;

[0010] Based on a preset knowledge base, the target perception data set and target fault types are fused and processed to determine the target fault identification result corresponding to the target dust removal workshop, and the target fault identification result is visualized based on the target workshop model.

[0011] According to another aspect of the present invention, a fault identification device based on digital twins is provided, comprising:

[0012] The data acquisition module is used to acquire the target sensor data set and target workshop model corresponding to the target dust removal workshop; wherein, the target workshop model is determined based on digital twin technology;

[0013] The data analysis module is used to perform data analysis on the target sensor data set based on the target machine learning model to determine the target sensing data set corresponding to the target dust removal workshop;

[0014] The type prediction module is used to predict the target sensing data set based on the target fault prediction model, and determine the target fault type corresponding to the target dust removal workshop.

[0015] The fault identification module is used to perform fusion processing on the target perception data set and target fault type based on a preset knowledge base, determine the target fault identification result corresponding to the target dust removal workshop, and visualize the target fault identification result based on the target workshop model.

[0016] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0017] At least one processor; and

[0018] A memory communicatively connected to the at least one processor; wherein,

[0019] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the fault identification method based on digital twins as described in any embodiment of the present invention.

[0020] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the fault identification method based on digital twins as described in any embodiment of the present invention.

[0021] According to another aspect of the present invention, a computer program product is provided, comprising a computer program that, when executed by a processor, implements the fault identification method based on digital twins as described in any embodiment of the present invention.

[0022] The technical solution of this invention involves acquiring a target sensor data set corresponding to the target dust removal workshop and a target workshop model determined based on digital twin technology. Then, based on a target machine learning model, data analysis is performed on the target sensor data set to determine the target perception data set corresponding to the target dust removal workshop. Further, based on a target fault prediction model, fault prediction is performed on the target perception data set to determine the target fault type corresponding to the target dust removal workshop. Finally, based on a preset knowledge base, the target perception data set and the target fault type are fused to determine the target fault identification result corresponding to the target dust removal workshop, and the target fault identification result is visualized based on the target workshop model. By constructing a high-fidelity digital twin system, real-time data acquisition and fusion of various detection indicators, multi-dimensional status monitoring, and intelligent early warning are achieved. This enables real-time perception, accurate mapping, in-depth analysis, and forward-looking prediction of the dust removal workshop's operating status, solving the problem of low reliability and operational efficiency in the waste collection and processing system, and improving the reliability and operational efficiency of the waste collection and processing system.

[0023] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0024] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0025] Figure 1 This is a flowchart of a fault identification method based on digital twins according to Embodiment 1 of the present invention;

[0026] Figure 2 This is a flowchart of a fault identification method based on digital twins according to Embodiment 2 of the present invention;

[0027] Figure 3 This is a flowchart of an optional fault identification method based on digital twins according to Embodiment 2 of the present invention;

[0028] Figure 4 This is a schematic diagram of the structure of a fault identification device based on digital twin according to Embodiment 3 of the present invention;

[0029] Figure 5 This is a schematic diagram of the structure of an electronic device that implements the fault identification method based on digital twins according to embodiments of the present invention. Detailed Implementation

[0030] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0031] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0032] Example 1

[0033] Figure 1 This is a flowchart of a fault identification method based on digital twins provided in Embodiment 1 of the present invention. This embodiment is applicable to situations where the operating status of a stalk collection and processing system in a silk-making workshop needs to be monitored in real time. The method can be executed by a fault identification device based on digital twins, which can be implemented in hardware and / or software and can be configured in an electronic device. Figure 1 As shown, the method includes:

[0034] S110. Obtain the target sensor data set and target workshop model corresponding to the target dust removal workshop; wherein, the target workshop model is determined based on digital twin technology.

[0035] In this context, a dust removal workshop can refer to a centralized and critical functional area within the silk-making process. Typically, a dust removal workshop is specifically responsible for collecting, filtering, and processing materials such as smoke, dust, and stalks generated during production to ensure clean production, material recycling, and safe operation. A target dust removal workshop can refer to a pre-selected dust removal workshop that requires status monitoring. For example, the target dust removal workshop can be determined based on actual application needs; this embodiment of the invention does not impose specific limitations on this. A sensor can refer to a detection device used to convert physical quantities, such as pressure, temperature, flow rate, vibration, or material level, into usable signals according to a certain rule. Typically, sensors are responsible for sensing and measuring the state of the physical world. Sensor data can refer to information collected and converted from the physical world by sensors, which can be recognized and processed by electronic devices. Target sensor data can refer to the final sensor data obtained after data processing. A target sensor data set can refer to the collection of target sensor data corresponding to the same target dust removal workshop at the same time. Typically, a target sensor data set can contain multiple target sensor data of different dimensions.

[0036] Among these, a workshop model refers to a virtual, visualized digital model created by using 3D modeling technology to achieve a high-precision, one-to-one digital replica of a physical workshop, such as its building structure, equipment layout, piping network, and electrical wiring. Digital twin technology refers to creating a symbiotic, data-driven, simulateable, and predictable intelligent virtual entity for the entire tobacco processing workshop or dust removal system. Typically, digital twin technology can transform a passive, experience-driven operation and maintenance model into a proactive, data-driven optimization and decision-making model through a closed-loop virtual-physical linkage, representing the ultimate technical framework for systematically solving all the pain points of traditional tobacco factory dust removal workshops. A target workshop model refers to the final workshop model generated using digital twin technology. Typically, a target workshop model can simulate the impact of different operations to aid in pre-planning and optimization decisions.

[0037] S120. Based on the target machine learning model, perform data analysis on the target sensor data set to determine the target perception data set corresponding to the target dust removal workshop.

[0038] In this context, a machine learning model can refer to a software system that automatically and intelligently learns patterns of normal behavior from massive amounts of historical and real-time data through algorithms, and thereby keenly detects slow changes or sudden situations deviating from these patterns. A target machine learning model can refer to the final trained machine learning model. Perceived data can refer to information used to represent the current operating status of equipment in a dust removal workshop. Target perceived data can refer to the perceived data corresponding to the target dust removal workshop at the current moment. A target perceived data set can refer to the set of various target perceived data corresponding to the target dust removal workshop at the same moment. Optionally, the target perceived data set includes: target data trends and target anomaly patterns. Data trends can refer to the direction and pattern of data changes over a long period, continuously, and slowly. For example, data trends can be pressure difference trends, energy consumption trends, and separation efficiency trends, etc. Target data trends can refer to the data trends corresponding to the target dust removal workshop at the current moment. Anomaly patterns can refer to special states or forms where data suddenly and significantly deviates from its historical normal range or expected behavior. For example, anomaly patterns can be sudden anomalies, correlated anomalies, and combined anomalies, etc. The target anomaly mode can refer to the anomaly mode corresponding to the target dust removal workshop at the current moment.

[0039] S130. Based on the target fault prediction model, perform fault prediction on the target perception data set to determine the target fault type corresponding to the target dust removal workshop.

[0040] Here, a fault prediction model refers to an intelligent analysis tool that, before a device or system experiences functional failure, uses its operational data, historical maintenance records, etc., and employs mathematical models and algorithms to predict the probability, severity, or remaining service life of a specific fault occurring within a specific future timeframe through the prediction of that fault. A target fault prediction model refers to the final, trained fault prediction model. A fault type refers to a specific category of fault. For example, fault types could be blockage risk, wear risk, and breakage risk. A target fault type can refer to the fault type corresponding to a specific piece of equipment in the target dust removal workshop within the predicted time period. For example, a target fault type could be that separator A has an 80% probability of becoming blocked after 8 hours.

[0041] S140. Based on a preset knowledge base, the target perception data set and target fault types are fused to determine the target fault identification result corresponding to the target dust removal workshop, and the target fault identification result is visualized based on the target workshop model.

[0042] The preset knowledge base refers to a pre-defined database used to transform the domain knowledge, equipment mechanisms, historical experience, and maintenance procedures of human experts into rules, cases, and models that the system can understand and apply. Fault identification results refer to the identification results used to represent the impact level of a fault type on the entire production line. Target fault identification results refer to the fault identification results corresponding to the target dust removal workshop. Visual display refers to the real-time display of parameters such as equipment on / off status, weight, and pressure. Typically, the visual display can use color flashing to indicate equipment that has malfunctioned or is issuing warnings.

[0043] The technical solution of this invention involves acquiring a target sensor data set corresponding to the target dust removal workshop and a target workshop model determined based on digital twin technology. Then, based on a target machine learning model, data analysis is performed on the target sensor data set to determine the target perception data set corresponding to the target dust removal workshop. Further, based on a target fault prediction model, fault prediction is performed on the target perception data set to determine the target fault type corresponding to the target dust removal workshop. Finally, based on a preset knowledge base, the target perception data set and the target fault type are fused to determine the target fault identification result corresponding to the target dust removal workshop, and the target fault identification result is visualized based on the target workshop model. By constructing a high-fidelity digital twin system, real-time data acquisition and fusion of various detection indicators, multi-dimensional status monitoring, and intelligent early warning are achieved. This enables real-time perception, accurate mapping, in-depth analysis, and forward-looking prediction of the dust removal workshop's operating status, solving the problem of low reliability and operational efficiency in the waste collection and processing system, and improving the reliability and operational efficiency of the waste collection and processing system.

[0044] Example 2

[0045] Figure 2 This is a flowchart of a fault identification method based on digital twins provided in Embodiment 2 of the present invention. This embodiment is a refinement based on the above embodiment. Specifically, it refines the "acquiring the target sensor data set corresponding to the target dust removal workshop". Specifically, it may include: collecting data from target equipment nodes in the target dust removal workshop based on a preset sensor group to obtain a basic sensor data set corresponding to the target dust removal workshop; and preprocessing the basic sensor data set based on preset data processing rules to obtain the target sensor data set corresponding to the target dust removal workshop. Figure 2 As shown, the method includes:

[0046] S210. Data is collected from the target equipment nodes in the target dust removal workshop based on the preset sensor group to obtain the basic sensor data set corresponding to the target dust removal workshop.

[0047] Here, a sensor group can refer to a collection of different sensors that collect data from multiple dimensions. For example, a sensor group may include high-precision weighing sensors, material blockage sensors, and vibration sensors, thus forming a multi-dimensional sensing network. A preset sensor group can refer to a pre-set sensor group used for data collection in the yarn processing workshop. For example, a preset sensor group may include temperature sensors, pressure sensors, vibration sensors, and flow sensors. An equipment node can refer to a key working node involved in the dust removal workshop. For example, an equipment node may include yarn processing and winding / packing. A target equipment node can refer to the equipment node corresponding to the target dust removal workshop. Basic sensor data can refer to the sensor data initially collected. For example, basic sensor data may be the temperature data, pressure data, vibration data, and flow data corresponding to the target equipment node at the current moment. A basic sensor data group can refer to a combination of basic sensor data corresponding to the same equipment node at the same collection moment. A basic sensor data set can refer to a collection of various basic sensor data groups within the same time period.

[0048] S220. Based on preset data processing rules, perform data preprocessing on the basic sensor data set to obtain the target sensor data set corresponding to the target dust removal workshop.

[0049] The preset data processing rules refer to pre-defined rules used to define the data preprocessing flow. For example, preset data processing rules may include operations such as data cleaning, noise reduction, data normalization, and feature extraction.

[0050] Specifically, in the data acquisition and transmission phase, data can be collected by deploying pre-set sensor groups on target equipment nodes in the target dust removal workshop, obtaining the basic sensor data set corresponding to the target dust removal workshop. Then, the data is transmitted to an edge gateway via wireless communication technology, and subsequently aggregated into a central server via a fiber optic network. The central server preprocesses the basic sensor data set based on pre-set data processing rules to obtain the target sensor data set corresponding to the target dust removal workshop, which is then stored persistently in a database to ensure a continuous and stable data supply.

[0051] S230. Obtain the target physical entity, basic workshop model, and preset embedding rules corresponding to the target dust removal workshop.

[0052] In this context, "physical entity" refers to the actual equipment existing in a real dust removal workshop and occupying physical space. "Target physical entity" refers to each physical entity corresponding to the target dust removal workshop. "Basic workshop model" refers to the initially constructed 3D digital model corresponding to the target dust removal workshop. Typically, the basic workshop model can contain virtual equipment that corresponds one-to-one with the target physical entities. "Preset embedded rules" refers to pre-defined rules used to limit the data early warning process. For example, the preset embedded rules could be that when the loading rate > 85% or the parameters are slightly abnormal, the system logs and prompts attention; or when the loading rate > 95% or the confidence level exceeds a threshold, the system pops up an alarm window and pushes information, requiring immediate action.

[0053] S240. Based on a preset digital twin platform, the target physical entity and the basic workshop model are mapped to obtain an intermediate workshop model corresponding to the target dust removal workshop. Based on preset embedding rules, the intermediate workshop model is optimized to obtain a target workshop model corresponding to the target dust removal workshop.

[0054] The pre-defined digital twin platform can refer to a pre-established industrial platform used to implement digital twin technology. The intermediate workshop model can refer to the workshop model obtained by data binding of the basic workshop model.

[0055] Specifically, before proceeding with the fault identification process, the target physical entity, basic workshop model, and preset embedding rules corresponding to the target dust removal workshop can be obtained first. Then, based on a preset digital twin platform, data mapping is performed on the target physical entity and the basic workshop model, establishing a binding relationship between the target physical entity in the database and the virtual equipment in the basic workshop model, resulting in an intermediate workshop model. Finally, the preset embedding rules are added to the intermediate workshop model to obtain the target workshop model. This provides a valid foundation for subsequent data processing.

[0056] It is worth noting that, in the embodiments of the present invention, the establishment process of the target workshop model can be completed before the use process. That is, the establishment process of the target workshop model can be completed before data collection or at the same time as data collection. The embodiments of the present invention are only illustrated by the above examples and do not limit the specific process order.

[0057] S250. Based on the target machine learning model, perform data analysis on the target sensor data set to determine the target perception data set corresponding to the target dust removal workshop.

[0058] In an optional implementation, before performing data analysis on the target sensor data set based on the target machine learning model to determine the target sensing data set corresponding to the target dust removal workshop, the method further includes:

[0059] Step a1: Obtain the first sensor data set and basic machine learning model corresponding to the target dust removal workshop; wherein, the first sensor data set includes historical sensor data groups, and each historical sensor data group includes corresponding historical equipment status tags.

[0060] Historical sensor data can refer to sensor data collected within a historical time period. A historical sensor data set can refer to a collection of historical sensor data within the same historical time period. Device status tags can refer to information used to represent the device status. For example, a device status tag can represent device health or a specific abnormal mode. Historical device status tags can refer to the device status tags corresponding to historical sensor data sets. Typically, one historical sensor data set corresponds to one historical device status tag. First sensor data can refer to historical sensor data sets collected within a historical time period. A first sensor data set can refer to a collection of historical sensor data sets within the same historical time period. Typically, a first sensor data set can contain multiple historical sensor data sets. A basic machine learning model can refer to a pre-built, untrained machine learning model. For example, a basic machine learning model can include a pre-set loading threshold.

[0061] Step a2: Train the basic machine learning model based on the first sensor data set to obtain the trained target machine learning model.

[0062] Specifically, before analyzing the target sensor dataset based on the target machine learning model to determine the target sensing dataset for the target dust removal workshop, a first sensor dataset containing historical sensor data and a basic machine learning model for the target dust removal workshop can be obtained first. Then, the first sensor dataset is input into the basic machine learning model, allowing it to analyze historical data spanning weeks or months, learning key parameters of the equipment under healthy conditions, such as fan current, dust removal efficiency, and the normal fluctuation range and long-term baseline of the overall system pressure difference. Furthermore, it learns the complex correlation patterns between multiple sensor readings during normal operation. For example, fan speed, pipeline pressure, and material flow rate have a specific equilibrium range under healthy conditions. This results in a well-trained target machine learning model.

[0063] For example, after inputting the target sensor dataset into the target machine learning model, the model can determine whether each sensor data group in the dataset is slowly but continuously deviating from a pre-learned historical baseline. If the model analysis finds that the average operating pressure of a pipeline has slowly increased by 5% over the past 30 days, while other parameters remain unchanged, a target data trend can be generated: the pipeline may have slight dust accumulation, leading to a slow increase in resistance, which may eventually cause blockage or increased energy consumption. Simultaneously, the model uses the complex correlation patterns between multiple pre-trained sensor readings to judge the target sensor dataset and obtain target anomaly patterns. Therefore, by monitoring the long-term change direction of key parameters, i.e., the target data trend, a basis can be provided for performance degradation early warning and preventative maintenance. By comparing the current data with the normal equilibrium range defined by the model in real time, sudden, unexpected operating states—i.e., target anomaly patterns—can be quickly detected, enabling early fault alarms.

[0064] S260. Based on the target fault prediction model, perform fault prediction on the target perception data set to determine the target fault type corresponding to the target dust removal workshop.

[0065] In an optional implementation, before performing fault prediction on the target sensing data set based on the target fault prediction model to determine the target fault type corresponding to the target dust removal workshop, the method further includes:

[0066] Step b1: Obtain historical fault data, historical degradation trend, second sensor data set and basic fault prediction model corresponding to the target dust removal workshop.

[0067] Here, fault data can refer to descriptive information used to represent equipment fault conditions. Historical fault data can refer to fault data corresponding to a historical time period. Decay trend can refer to the data trend indicating data decay. Historical decay trend can refer to the decay trend corresponding to a historical time period. Second sensor data can refer to sensor data collected before a set time period under equipment fault conditions with historical fault data and historical decay trends. Second sensor data set can refer to the set composed of various second sensor data corresponding to the same historical time period. Basic fault prediction model can refer to a preliminary, untrained fault prediction model. For example, the basic fault prediction model can include a vibration spectrum analysis strategy.

[0068] It is worth noting that, in the embodiments of the present invention, the historical time periods corresponding to the first sensor data set and the second sensor data set can be the same time interval or different time intervals, and the embodiments of the present invention do not specifically limit this.

[0069] Step b2: Train the basic fault prediction model based on historical fault data, historical degradation trends and the second sensor data set to obtain the trained target fault prediction model.

[0070] Specifically, before predicting the target fault type of the target dust removal workshop based on the target sensing data set using the target fault prediction model, historical fault data, historical degradation trends, second sensor data sets, and the basic fault prediction model for the target dust removal workshop can be obtained first. Then, the historical fault data, historical degradation trends, and second sensor data sets for the target dust removal workshop are input into the basic fault prediction model. The basic fault prediction model uses the historical fault data and historical degradation trends to label the second sensor data set and learns the complex mapping relationship between the label results and the second sensor data set, thus obtaining a trained target fault prediction model.

[0071] For example, after inputting the target sensing data set into the target fault prediction model, the model can integrate long-term trends and in-depth analysis to generate predictions about potential future faults and their occurrence times. This allows raw, isolated sensor data to be gradually transformed into maintenance decisions with clear guidance. By comprehensively analyzing multiple parameters such as material drop rate, weight change trends, and pipeline pressure, the risk of material blockage can be predicted in advance, effectively solving core problems in existing technologies such as sensing lag, passive response, and low prediction accuracy.

[0072] S270. Based on a preset knowledge base, the target perception data set and target fault types are fused to determine the target fault identification result corresponding to the target dust removal workshop, and the target fault identification result is visualized based on the target workshop model.

[0073] For example, after obtaining the target perception data set and target fault type corresponding to the target dust removal workshop, a pre-set knowledge base can be used for fusion and reasoning. For instance, it can be used to determine whether a pressure anomaly is a precursor to a minor blockage or a serious fault. This generates an easy-to-understand diagnostic conclusion, i.e., the target fault identification result, such as a moderate risk of blockage at the cyclone separator inlet. Furthermore, the target workshop model is used to visualize the target fault identification result, allowing parameters such as equipment status, material flow rate, and pressure changes in the material collection and processing system to be presented intuitively.

[0074] In an optional implementation, after fusing the target sensing data set and target fault types based on a preset knowledge base to determine the target fault identification result corresponding to the target dust removal workshop, the method further includes: performing data matching on the target fault identification result based on the preset knowledge base to determine the target maintenance suggestion corresponding to the target dust removal workshop. The maintenance suggestion can refer to a specific and operable maintenance measure plan. For example, the maintenance suggestion could be to clean the A-line separator within 4 hours. The target maintenance suggestion can refer to the maintenance suggestion corresponding to the target dust removal workshop. Specifically, after fusing the target sensing data set and target fault types based on the preset knowledge base to determine the target fault identification result corresponding to the target dust removal workshop, data matching can be performed on the preset knowledge base using the target fault identification result to determine the maintenance suggestion corresponding to the target fault identification result, which serves as the target maintenance suggestion. This forms a closed-loop intelligent management platform encompassing physical entity, virtual model, data interaction, and intelligent decision-making. By assisting maintenance personnel in quickly formulating scientific maintenance plans, the maintenance process shifts from passive response to proactive prediction and precise maintenance, improving the reliability of the waste collection and processing system.

[0075] The technical solution of this invention involves collecting data from target equipment nodes in a target dust removal workshop based on a preset sensor group to obtain a basic sensor data set corresponding to the target dust removal workshop. This basic sensor data set is then preprocessed according to preset data processing rules to obtain a target sensor data set corresponding to the target dust removal workshop. Next, the target physical entity, basic workshop model, and preset embedding rules corresponding to the target dust removal workshop are acquired. Data mapping of the target physical entity and basic workshop model is performed based on a preset digital twin platform to obtain an intermediate workshop model corresponding to the target dust removal workshop. This intermediate workshop model is then optimized according to preset embedding rules to obtain a target workshop model corresponding to the target dust removal workshop. Further, data analysis is performed on the target sensor data set based on a target machine learning model to determine the target perception data set corresponding to the target dust removal workshop. Further, fault prediction is performed on the target perception data set based on a target fault prediction model to determine the target fault type corresponding to the target dust removal workshop. Finally, the target perception data set and target fault type are fused based on a preset knowledge base to determine the target fault identification result corresponding to the target dust removal workshop, and the target fault identification result is visualized based on the target workshop model. By constructing a high-fidelity digital twin system, real-time data acquisition and integration of various detection indicators, multi-dimensional status monitoring and intelligent early warning are achieved. This enables real-time perception, accurate mapping, in-depth analysis and forward-looking prediction of the operating status of the dust removal workshop, solving the problems of low reliability and low operation and maintenance efficiency of the waste collection and processing system, and improving the reliability and operation and maintenance efficiency of the waste collection and processing system.

[0076] Figure 3 The diagram shows a flowchart of an optional fault identification method based on digital twins provided by an embodiment of the present invention. Specifically, the fault identification method based on digital twins includes four stages: data acquisition and transmission, digital twin modeling and simulation, data analysis and intelligent processing, and application and decision support. In the data acquisition and transmission stage: First, data is acquired by deploying a preset sensor group on the target equipment node in the target dust removal workshop, obtaining a basic sensor data set corresponding to the target dust removal workshop. Then, the basic sensor data set is transmitted to an edge gateway via wireless communication technology, then aggregated into a central server via a fiber optic network, and stored persistently in a database. In the digital twin modeling and simulation stage: First, a basic workshop model corresponding to the target dust removal workshop is constructed using modeling tools. Then, the target physical entity and preset embedding rules corresponding to the target dust removal workshop are obtained. The basic workshop model, target physical entity, and preset embedding rules are imported into a preset digital twin platform. The target physical entity and basic workshop model are mapped using the preset digital twin platform to obtain an intermediate workshop model corresponding to the target dust removal workshop. Based on the preset embedding rules, the intermediate workshop model is optimized to obtain the target workshop model corresponding to the target dust removal workshop. In the data analysis and intelligent processing stage: First, based on preset data processing rules, the basic sensor data set is preprocessed to obtain the target sensor data set corresponding to the target dust removal workshop. Then, the target sensor data set is input into a target machine learning model, which analyzes the data to determine the target perception data set corresponding to the target dust removal workshop, including target data trends and target anomaly patterns. In the application and decision support stage: First, the target perception data set is input into a target fault prediction model, which predicts faults in the target perception data set to determine the target fault type corresponding to the target dust removal workshop. Then, a preset knowledge base is used to fuse the target perception data set and the target fault type to determine the target fault identification result corresponding to the target dust removal workshop. Finally, based on the preset knowledge base, data matching is performed on the target fault identification result to determine the target maintenance recommendations for the target dust removal workshop. This completes the entire process of the fault identification method based on digital twins.

[0077] Example 3

[0078] Figure 4 This is a schematic diagram of a fault identification device based on digital twins provided in Embodiment 3 of the present invention. Figure 4 As shown, the device includes: a data acquisition module 310, a data analysis module 320, a type prediction module 330, and a fault identification module 340;

[0079] The data acquisition module 310 is used to acquire the target sensor data set and the target workshop model corresponding to the target dust removal workshop; wherein the target workshop model is determined based on digital twin technology.

[0080] Data analysis module 320 is used to perform data analysis on the target sensor data set based on the target machine learning model to determine the target sensing data set corresponding to the target dust removal workshop;

[0081] Type prediction module 330 is used to perform fault prediction on the target perception data set based on the target fault prediction model, and determine the target fault type corresponding to the target dust removal workshop.

[0082] The fault identification module 340 is used to perform fusion processing on the target perception data set and target fault type based on a preset knowledge base, determine the target fault identification result corresponding to the target dust removal workshop, and visualize the target fault identification result based on the target workshop model.

[0083] The technical solution of this invention involves acquiring a target sensor data set corresponding to the target dust removal workshop and a target workshop model determined based on digital twin technology. Then, based on a target machine learning model, data analysis is performed on the target sensor data set to determine the target perception data set corresponding to the target dust removal workshop. Further, based on a target fault prediction model, fault prediction is performed on the target perception data set to determine the target fault type corresponding to the target dust removal workshop. Finally, based on a preset knowledge base, the target perception data set and the target fault type are fused to determine the target fault identification result corresponding to the target dust removal workshop, and the target fault identification result is visualized based on the target workshop model. By constructing a high-fidelity digital twin system, real-time data acquisition and fusion of various detection indicators, multi-dimensional status monitoring, and intelligent early warning are achieved. This enables real-time perception, accurate mapping, in-depth analysis, and forward-looking prediction of the dust removal workshop's operating status, solving the problem of low reliability and operational efficiency in the waste collection and processing system, and improving the reliability and operational efficiency of the waste collection and processing system.

[0084] Optionally, the data acquisition module 310 can be used for:

[0085] Data is collected from the target equipment nodes in the target dust removal workshop based on a preset sensor group to obtain the basic sensor data set corresponding to the target dust removal workshop.

[0086] Based on preset data processing rules, the basic sensor data set is preprocessed to obtain the target sensor data set corresponding to the target dust removal workshop.

[0087] Optionally, the data acquisition module 310 can be used for:

[0088] Obtain the target physical entity, basic workshop model, and preset embedding rules corresponding to the target dust removal workshop;

[0089] Based on a preset digital twin platform, the target physical entity and the basic workshop model are mapped to obtain an intermediate workshop model corresponding to the target dust removal workshop. The intermediate workshop model is then optimized based on preset embedding rules to obtain the target workshop model corresponding to the target dust removal workshop.

[0090] Optionally, the target perception data set includes: target data trends and target anomaly patterns.

[0091] Optionally, the fault identification device based on digital twins may further include: a first model training module, used to acquire a first sensor data set and a basic machine learning model corresponding to the target dust removal workshop before performing data analysis on the target sensor data set based on the target machine learning model to determine the target perception data set corresponding to the target dust removal workshop; wherein, the first sensor data set includes historical sensor data groups, and each historical sensor data group includes a corresponding historical equipment status label; and the basic machine learning model is trained based on the first sensor data set to obtain a trained target machine learning model.

[0092] Optionally, the fault identification device based on digital twin may further include: a second model training module, used to acquire historical fault data, historical decay trends, a second sensor data set, and a basic fault prediction model corresponding to the target dust removal workshop before performing fault prediction on the target sensing data set based on the target fault prediction model to determine the target fault type corresponding to the target dust removal workshop; and to train the basic fault prediction model based on the historical fault data, historical decay trends, and the second sensor data set to obtain a trained target fault prediction model.

[0093] Optionally, the fault identification device based on digital twin may further include: a suggestion determination module, used to determine the target maintenance suggestion corresponding to the target dust removal workshop by performing data matching on the target fault identification result based on the preset knowledge base after the target perception data set and target fault type are fused based on the preset knowledge base.

[0094] The fault identification device based on digital twin provided in the embodiments of the present invention can execute the fault identification method based on digital twin provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the method execution.

[0095] Example 4

[0096] Figure 5 A schematic diagram of an electronic device 410 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0097] like Figure 5 As shown, the electronic device 410 includes at least one processor 420 and a memory, such as a read-only memory (ROM) 430 or a random access memory (RAM) 440, communicatively connected to the at least one processor 420. The memory stores computer programs executable by the at least one processor. The processor 420 can perform various appropriate actions and processes based on the computer program stored in the ROM 430 or loaded into the RAM 440 from storage unit 490. The RAM 440 may also store various programs and data required for the operation of the electronic device 410. The processor 420, ROM 430, and RAM 440 are interconnected via a bus 450. An input / output (I / O) interface 460 is also connected to the bus 450.

[0098] Multiple components in electronic device 410 are connected to I / O interface 460, including: input unit 470, such as keyboard, mouse, etc.; output unit 480, such as various types of monitors, speakers, etc.; storage unit 490, such as disk, optical disk, etc.; and communication unit 4100, such as network card, modem, wireless transceiver, etc. Communication unit 4100 allows electronic device 410 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0099] Processor 420 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 420 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 420 performs the various methods and processes described above, such as fault identification methods based on digital twins.

[0100] The method includes:

[0101] Acquire the target sensor data set and target workshop model corresponding to the target dust removal workshop; wherein, the target workshop model is determined based on digital twin technology;

[0102] Based on the target machine learning model, data analysis is performed on the target sensor data set to determine the target sensing data set corresponding to the target dust removal workshop;

[0103] Based on the target fault prediction model, fault prediction is performed on the target sensing data set to determine the target fault type corresponding to the target dust removal workshop;

[0104] Based on a preset knowledge base, the target perception data set and target fault types are fused and processed to determine the target fault identification result corresponding to the target dust removal workshop, and the target fault identification result is visualized based on the target workshop model.

[0105] In some embodiments, the digital twin-based fault identification method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 490. In some embodiments, part or all of the computer program may be loaded and / or installed on electronic device 410 via ROM 430 and / or communication unit 4100. When the computer program is loaded into RAM 440 and executed by processor 420, one or more steps of the digital twin-based fault identification method described above may be performed. Alternatively, in other embodiments, processor 420 may be configured to perform the digital twin-based fault identification method by any other suitable means (e.g., by means of firmware).

[0106] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), system-on-a-chip (SoCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0107] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0108] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0109] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0110] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0111] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0112] This application also discloses a computer program product, which includes a computer program that, when executed by a processor, implements the digital twin-based fault identification method provided in any embodiment of this application. This program product shares the same inventive concept as the digital twin-based fault identification methods disclosed in the embodiments of this application, and therefore will not be described in detail here.

[0113] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0114] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A fault identification method based on digital twins, characterized in that, include: Acquire the target sensor data set and target workshop model corresponding to the target dust removal workshop; wherein, the target workshop model is determined based on digital twin technology; Based on the target machine learning model, data analysis is performed on the target sensor data set to determine the target sensing data set corresponding to the target dust removal workshop; Based on the target fault prediction model, fault prediction is performed on the target sensing data set to determine the target fault type corresponding to the target dust removal workshop; Based on a preset knowledge base, the target perception data set and target fault types are fused and processed to determine the target fault identification result corresponding to the target dust removal workshop, and the target fault identification result is visualized based on the target workshop model.

2. The method according to claim 1, characterized in that, The acquisition of the target sensor data set corresponding to the target dust removal workshop includes: Data is collected from the target equipment nodes in the target dust removal workshop based on a preset sensor group to obtain the basic sensor data set corresponding to the target dust removal workshop. Based on preset data processing rules, the basic sensor data set is preprocessed to obtain the target sensor data set corresponding to the target dust removal workshop.

3. The method according to claim 1, characterized in that, Obtain the target workshop model corresponding to the target dust removal workshop, including: Obtain the target physical entity, basic workshop model, and preset embedding rules corresponding to the target dust removal workshop; Based on a preset digital twin platform, the target physical entity and the basic workshop model are mapped to obtain an intermediate workshop model corresponding to the target dust removal workshop. The intermediate workshop model is then optimized based on preset embedding rules to obtain the target workshop model corresponding to the target dust removal workshop.

4. The method according to claim 1, characterized in that, The target perception data set includes: target data trends and target anomaly patterns.

5. The method according to claim 1, characterized in that, Before performing data analysis on the target sensor data set based on the target machine learning model to determine the target sensing data set corresponding to the target dust removal workshop, the method further includes: Obtain the first sensor data set and basic machine learning model corresponding to the target dust removal workshop; wherein, the first sensor data set includes historical sensor data groups, and each historical sensor data group includes corresponding historical equipment status tags; The basic machine learning model is trained based on the first sensor data set to obtain the trained target machine learning model.

6. The method according to claim 1, characterized in that, Before performing fault prediction on the target sensing data set based on the target fault prediction model to determine the target fault type corresponding to the target dust removal workshop, the method further includes: Acquire historical fault data, historical degradation trends, second sensor data set, and basic fault prediction model corresponding to the target dust removal workshop; The basic fault prediction model is trained based on historical fault data, historical degradation trends, and a second sensor dataset to obtain a trained target fault prediction model.

7. The method according to claim 1, characterized in that, After fusing the target perception data set and target fault types based on a preset knowledge base to determine the target fault identification result corresponding to the target dust removal workshop, the method further includes: Based on a preset knowledge base, the target fault identification results are matched to determine the target maintenance recommendations corresponding to the target dust removal workshop.

8. A fault identification device based on digital twins, characterized in that, include: The data acquisition module is used to acquire the target sensor data set and target workshop model corresponding to the target dust removal workshop; wherein, the target workshop model is determined based on digital twin technology; The data analysis module is used to perform data analysis on the target sensor data set based on the target machine learning model to determine the target sensing data set corresponding to the target dust removal workshop; The type prediction module is used to predict the target sensing data set based on the target fault prediction model, and determine the target fault type corresponding to the target dust removal workshop. The fault identification module is used to perform fusion processing on the target perception data set and target fault type based on a preset knowledge base, determine the target fault identification result corresponding to the target dust removal workshop, and visualize the target fault identification result based on the target workshop model.

9. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the fault identification method based on digital twins as described in any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the fault identification method based on digital twins as described in any one of claims 1-7.

Images