Workshop visual monitoring platform and method based on digital twinning

Abstract

The application discloses a workshop visual monitoring platform and method based on digital twinning, belongs to the technical field of industrial manufacturing visualization, and comprises a data acquisition module, the data acquisition module comprises an acquisition unit, an environment monitoring unit and a video monitoring unit; the acquisition unit is used for acquiring operation parameters of production equipment; the environment monitoring unit is used for monitoring environment parameters of a workshop; the environment parameters comprise humidity, temperature and air quality; the video monitoring unit is used for monitoring a production process of the production equipment; a data processing module, the data processing module is responsive to the data acquisition module and is used for processing the operation parameters and the environment parameters. Through the setting of a risk threshold value and the automatic updating of the operation state of the production equipment, the application can provide automatic decision support for the production process, reduces the need for manual intervention, improves the automation degree and decision efficiency of the production process, and makes the production management of enterprises more intelligent and efficient.

Description

Technical Field

[0001] This invention relates to the field of industrial manufacturing visualization technology, and in particular to a workshop visualization monitoring platform and method based on digital twins. Background Technology

[0002] In modern industrial production, workshop monitoring and management are crucial for improving production efficiency, ensuring product quality, and guaranteeing production safety. Traditional monitoring methods mainly rely on manual inspections, distributed sensor data collection, and simple video surveillance systems, which have many limitations.

[0003] Regarding this research, application CN202411053988.8 provides an intelligent workshop control system and method based on digital twin visualization technology. This technical solution includes a workshop data acquisition module, a workshop data analysis module, a workshop data service module, and a workshop data control module. The workshop data acquisition module is responsible for collecting data. The data analysis module calculates the workshop protection unit based on the workshop encryption index Qiy, the virtual workshop data homomorphic encryption index Rrz, the privacy protection index Bzf, and the access control coefficient Wrq. The workshop data service module adds or removes data encryption tools at the connection points between all modules based on the workshop encryption index Qiy, the virtual workshop data homomorphic encryption index Rrz, and the privacy protection index Bzf. This technical solution can ensure that the virtual workshop maintains data security and privacy while operating efficiently.

[0004] Another application, CN202410817883.9, provides a method and system for visual monitoring of manufacturing workshops based on digital twins. This technical solution includes acquiring the motion scene of production equipment in the workshop and constructing a digital twin model based on the historical motion of the equipment entities. Various equipment sensors are set in the digital twin model of the entities. Process data of equipment operation is collected, processed, and stored as multi-source heterogeneous data. The system monitors the equipment operating status information acquired by the equipment sensors during production, filters the operating status information data, and performs predictive analysis of the equipment's operating route. This technical solution updates the digital twin model of the entities based on the monitoring information; it also builds a visual monitoring platform to provide users with real-time monitoring information and achieve overall control of the production process.

[0005] However, the above-mentioned technical solutions still have shortcomings. In reality, as production activities in the workshop proceed, factors such as equipment wear and tear, process adjustments, and environmental changes can all cause changes in the state of physical entities. The updates to digital twin models often lag behind, failing to reflect the latest state of the physical entity in real time. For example, after long-term operation, equipment may experience wear and tear, causing changes in its performance parameters. However, the model may not be able to update these changes in a timely manner, leading to discrepancies between monitoring results and actual conditions. Summary of the Invention

[0006] In view of the problems existing in the field of industrial manufacturing visualization technology, the present invention is proposed.

[0007] Therefore, one of the objectives of this invention is to provide a workshop visualization monitoring platform and method based on digital twins. By setting risk thresholds and automatically updating the operating status of production equipment, it can provide automated decision support for the production process, reduce the need for manual intervention, improve the automation level and decision efficiency of the production process, and make the enterprise's production management more intelligent and efficient.

[0008] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0009] On the one hand, the present invention provides a workshop visualization monitoring platform based on digital twins, including:

[0010] The data acquisition module includes an acquisition unit, an environmental monitoring unit, and a video surveillance unit.

[0011] The data acquisition unit is used to collect the operating parameters of the production equipment;

[0012] The environmental monitoring unit is used to monitor the environmental parameters of the workshop; these parameters include humidity, temperature, and air quality.

[0013] The video surveillance unit is used to monitor the production process of the production equipment;

[0014] The data processing module responds to the data acquisition module and is used to process operating parameters and environmental parameters; the data fusion module is used to fuse the processed operating parameters and environmental parameters, and to build a digital twin model to analyze the correlation between changes in environmental parameters and operating parameters.

[0015] The LSTM network fusion processing module is used to fuse the analyzed correlation effects; the LSTM network fusion processing module includes a differentiation unit, an analysis unit, a calculation unit, and an update unit;

[0016] The differentiation unit is used to classify the analyzed associated impacts into mild, moderate and severe levels, and to analyze the characteristic changes of environmental parameters in different levels of impact.

[0017] The analysis unit, based on the principle of mild impact, analyzes the parameters that cause mild impact according to environmental parameters, marks the parameters as the first environmental parameters, and generates a parameter group based on the first environmental parameters. The parameter group includes the 10 to 15 parameters that appear most frequently. The calculation unit responds to the parameter group and calculates the regular changes of each parameter in the parameter group.

[0018] The update unit is used to update the operating status of the production equipment according to the parameter group. When the environmental parameters collected in a future time period are the same as any parameter in the parameter group, the operating status of the production equipment is updated to a slightly affected fault state. As a preferred embodiment of the present invention, the data processing module performs cleaning, filtering, and format conversion on the operating parameters and environmental parameters, as well as removing noisy data and outliers.

[0019] It also includes data analysis and feature extraction of operating parameters and environmental parameters; among which, data analysis includes calculating the average operating time of production equipment, and calculating the average interval between equipment failures based on the average operating time, as well as the mean and variance of the workshop's environmental parameters;

[0020] Feature extraction includes dimensionality reduction and feature extraction of the operating parameters and environmental parameters of the generating equipment using machine learning algorithms. In a preferred embodiment of the present invention, the processed operating parameters and environmental parameters are fused in the data fusion module, including fusion using a physical model fusion method, fusing the operating parameters and environmental parameters of the generating equipment according to the physical principles of the production equipment and the physical environment of the workshop.

[0021] It also includes data-driven model fusion, which uses machine learning algorithms to build data-driven models of the operating parameters and environmental parameters of the generating device, in order to fuse the operating parameters and environmental parameters. Machine learning algorithms include support vector machines and neural networks.

[0022] In a preferred embodiment of the present invention, the regular changes of each parameter in the calculation parameter group are calculated in the calculation unit according to the following formula:

[0023] Where θ represents the air quality index of the workshop;

[0024] In the formula, C i C represents the concentration of the i-th pollutant. max，i and C min，i I represents the highest and lowest concentrations of the i-th pollutant, respectively. min，i and I max，i These represent the lowest and highest air quality indices for the i-th pollutant, respectively.

[0025] In a preferred embodiment of the present invention, the calculation of the regular changes of each parameter in the parameter group further includes calculating it according to the following formula:

[0026] Where η represents the diffusion rate of pollutants over time;

[0027] In the formula, C represents the concentration of pollutants, t represents time, D represents the diffusion coefficient of pollutants, u represents wind speed, and S represents the source term of pollutants; This represents the Laplace operator.

[0028] In a preferred embodiment of the present invention, the environmental parameters causing a moderate impact are predicted based on the calculated regular changes, and the prediction method includes:

[0029] The maximum and median parameters are obtained from the parameter set. The pattern of the median parameter changing towards the maximum parameter is analyzed. Based on this pattern, the difference between adjacent parameters between the median and the maximum parameter is obtained. The average difference is calculated based on these differences, and a risk threshold is preset using the average difference. When the average difference of environmental parameters collected in future time periods exceeds the risk threshold, the operating status of the production equipment is updated to a moderately affected fault state, and the average difference is marked as a reference value. In a preferred embodiment of this invention: if the operating status of the production equipment is updated to a slightly affected fault state, changes in operating parameters are collected based on the parameters corresponding to the slightly affected fault state. Abnormal changes in the production equipment are obtained based on the changes in operating parameters and the video of the monitored production process. If the changes in operating parameters are less than the difference between adjacent parameters obtained between the median and the maximum parameter, the update of the operating status of the production equipment to a slightly affected fault state is cancelled.

[0030] In a preferred embodiment of the present invention, if the change in the operating parameter is less than the difference between adjacent parameters obtained between the median parameter and the maximum parameter, a monitoring period is preset for the change in the operating parameter. The monitoring period is preset based on the time taken for the median parameter to change to the maximum parameter, and the duration of the monitoring period is at least one-third of the time taken. During the monitoring period, if the average difference corresponding to the change in the operating parameter is half of the reference value, the operating status of the production equipment is updated to a slightly affected fault state.

[0031] On the other hand, the present invention provides a method for applying the above-mentioned digital twin-based workshop visualization monitoring platform, comprising the following steps:

[0032] Collect operating parameters of production equipment and environmental parameters of the workshop, and monitor the production process of the production equipment;

[0033] Processing operating parameters and environmental parameters, including cleaning, filtering, and format conversion of operating parameters and environmental parameters, as well as removing noisy data and outliers;

[0034] The processed operating parameters and environmental parameters are fused together, and a digital twin model is constructed to analyze the correlation between changes in environmental parameters and operating parameters.

[0035] The analyzed associated impacts are integrated, including classifying them into mild, moderate and severe impacts in a tiered manner, and analyzing the characteristic changes of environmental parameters in different degrees of impact.

[0036] Based on the analysis of environmental parameters, parameters that cause a slight impact are marked as the first environmental parameter; and a parameter group is generated based on the first environmental parameter, which includes the 10 to 15 parameters that appear most frequently, and the regular changes of each parameter in the parameter group are calculated.

[0037] The operating status of the production equipment is updated based on the parameter set. When the environmental parameters collected in a future time period are the same as any parameter in the parameter set, the operating status of the production equipment is updated to a fault state that is slightly affected.

[0038] Beneficial effects:

[0039] 1. The LSTM network fusion processing module fuses the analyzed correlations and the differentiation unit distinguishes the degree of influence in a tiered manner. This processing method can automatically learn and identify complex patterns and rules in the data, thereby more accurately updating the operating status of the production equipment. For example, for minor influences, the analysis and calculation units determine the key environmental parameters and their changing patterns, and update the operating status of the production equipment accordingly, thus identifying potential faults in advance.

[0040] 2. The update unit updates the operating status of the production equipment according to the parameter group, and can dynamically adjust the operating status of the production equipment according to the environmental parameters collected in the future. This dynamic update mechanism enables the monitoring platform to reflect the actual operating status of the production equipment in real time, promptly detect potential fault risks, and adjust the operating strategy of the production equipment according to the actual situation to reduce the impact of production equipment failure on production.

[0041] 3. When the operating status of the production equipment is updated to a slightly affected fault state, abnormal changes in the production equipment can be obtained based on changes in operating parameters and video of the production process, and it can be determined whether to lift the fault state. In addition, a preset monitoring period is set to continuously monitor changes in operating parameters. This mechanism not only avoids misjudgments caused by short-term fluctuations in environmental parameters, but also reacts in a timely manner when there are substantial changes in the operating status of the production equipment, further improving the accuracy and reliability of predicting and handling the operating status. Attached Figure Description

[0042] To more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings used in the following description of the embodiments will be briefly introduced. Obviously, the 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.

[0043] in:

[0044] Figure 1 This is a schematic diagram of the modular structure of a workshop visualization monitoring platform based on digital twins according to an embodiment of the present invention;

[0045] Figure 2 This is a schematic diagram of the method flow according to an embodiment of the present invention;

[0046] The diagram is labeled as follows: 110 - Data acquisition module; 1101 - Acquisition unit; 1102 - Environmental monitoring unit; 1103 - Video monitoring unit; 120 - Data processing module; 130 - Data fusion module; 140 - LSTM network fusion processing module; 1401 - Differentiation unit; 1402 - Analysis unit; 1403 - Calculation unit; 1404 - Update unit. Detailed Implementation

[0047] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the described embodiments of the present invention are within the scope of protection of the present invention.

[0048] Because existing digital twin models have a certain lag in updates, they cannot reflect the latest state of physical entities in real time, resulting in monitoring results that do not match the actual situation.

[0049] Based on this, the present invention proposes a workshop visualization monitoring platform and method based on digital twins. By setting risk thresholds and automatically updating the operating status of production equipment, it can provide automated decision support for the production process, reduce the need for manual intervention, improve the automation level and decision-making efficiency of the production process, and make enterprise production management more intelligent and efficient. The following embodiments, in conjunction with the accompanying drawings, further illustrate this solution in detail.

[0050] Reference Figures 1 to 2 As one embodiment of the present invention, this embodiment provides a workshop visualization monitoring platform based on digital twins, including:

[0051] The data acquisition module 110 includes an acquisition unit 1101, an environmental monitoring unit 1102, and a video monitoring unit 1103.

[0052] The acquisition unit 1101 is used to acquire the operating parameters of the production equipment;

[0053] In this embodiment, various types of sensors, such as temperature sensors, pressure sensors, vibration sensors, and current sensors, are installed on the designated production equipment to collect parameter data during the operation of the production equipment.

[0054] Environmental monitoring unit 1102 is used to monitor environmental parameters in the workshop; these parameters include humidity, temperature, and air quality.

[0055] In this embodiment, environmental monitoring equipment deployed in the workshop, such as temperature and humidity sensors and air quality sensors, is used to monitor the environmental conditions of the workshop and ensure that the production environment meets the process requirements.

[0056] Video monitoring unit 1103 is used to monitor the production process of production equipment;

[0057] In this embodiment, high-definition cameras are installed at key locations on designated production equipment to achieve real-time video monitoring of the production process; this is used to assist in monitoring and post-event traceability analysis.

[0058] The data processing module 120 responds to the data acquisition module and is used to process operating parameters and environmental parameters; the data fusion module 130 is used to fuse the processed operating parameters and environmental parameters, construct a digital twin model, and analyze the correlation between changes in environmental parameters and operating parameters.

[0059] The LSTM network fusion processing module 140 is used to fuse the analyzed correlation effects; the LSTM network fusion processing module 140 includes a differentiation unit 1401, an analysis unit 1402, a calculation unit 1403 and an update unit 1404.

[0060] The differentiation unit 1401 is used to differentiate the analyzed associated impacts into mild, moderate and severe impacts in a stepwise manner, and to analyze the characteristic changes of environmental parameters in different degrees of impact.

[0061] The analysis unit 1402 is based on the mild impact and is used to analyze the parameters that cause the mild impact according to environmental parameters, mark the parameters as the first environmental parameters, and generate a parameter group based on the first environmental parameters. The parameter group includes the 10 to 15 parameters that appear most frequently. The calculation unit 1403 responds to the parameter group and is used to calculate the regular changes of each parameter in the parameter group.

[0062] The update unit 1404 is used to update the operating status of the production equipment according to the parameter group. When the environmental parameters collected in the future period are the same as any parameter in the parameter group, the operating status of the production equipment is updated to a fault state that is slightly affected.

[0063] To further explain, by collecting the operating parameters of production equipment and the environmental parameters of the workshop in real time, and combining them with video monitoring, the monitoring platform can reflect the actual situation of the workshop in real time, providing timely and accurate information for production management.

[0064] By utilizing digital twin models and LSTM networks, in-depth analysis and processing of data are achieved, which can automatically identify the degree of impact of changes in environmental parameters on the operation of production equipment and update the operating status of production equipment accordingly, thereby improving the level of intelligence in monitoring.

[0065] In the data processing module, the operating parameters and environmental parameters are cleaned, filtered, and converted in format, as well as noise data and outliers are removed;

[0066] It also includes data analysis and feature extraction of operating parameters and environmental parameters; among which, data analysis includes calculating the average operating time of production equipment, and calculating the average interval between equipment failures based on the average operating time, as well as the mean and variance of the workshop's environmental parameters;

[0067] In this embodiment, these statistics can be used to understand the basic situation of the equipment operation and workshop environment, providing basic data for subsequent monitoring and optimization;

[0068] Feature extraction includes dimensionality reduction and feature extraction of the operating parameters and environmental parameters of the generated device using machine learning algorithms. In this embodiment, feature extraction based on machine learning is performed by using machine learning algorithms such as principal component analysis (PCA) and linear discriminant analysis (LDA) to reduce the dimensionality and extract features of the operating parameters and environmental parameters of the generated device. For example, principal component analysis (PCA) is used to extract the main components of the operating parameters and environmental parameters of the device, reducing the data dimensionality while retaining the main information of the data, thereby improving the efficiency and accuracy of subsequent training and analysis of the digital twin model.

[0069] To further explain, this embodiment, through data analysis and feature extraction, uses machine learning algorithms to reduce the dimensionality of the data and extract features, which can uncover useful information hidden in the data, further enhance the value of the data, and provide stronger support for subsequent production equipment failure prediction and production process optimization.

[0070] In the data fusion module, the processed operating parameters and environmental parameters are fused, including fusion by means of physical model fusion, which generates the fusion of operating parameters and environmental parameters of the equipment based on the physical principles of the production equipment and the physical environment of the workshop;

[0071] In this embodiment, for example, for motor equipment, the operating parameters of the motor such as current, voltage, and power are integrated with environmental parameters such as ambient temperature and ventilation conditions in the workshop according to the thermodynamic model of the motor. The actual operating temperature of the motor is calculated through the thermodynamic model, and the overheating fault that may occur in the motor can be predicted in advance.

[0072] It also includes fusion using a data-driven model fusion approach, which uses machine learning algorithms to build a data-driven model of the operating parameters and environmental parameters of the generating device, in order to fuse the operating parameters and environmental parameters. The machine learning algorithms include support vector machines and neural networks.

[0073] In this embodiment, for example, a neural network model is trained using a data-driven model. The vibration data of the generating equipment and the noise data of the workshop are taken as inputs to the neural network model, and the fault status of the production equipment is taken as output. By fusing operating parameters and environmental parameters through the neural network model, the accuracy of fault diagnosis is improved.

[0074] To further explain, this embodiment adopts a combination of physical model fusion and data-driven model fusion, which takes into account both the physical principles of the production equipment and the physical environment of the workshop, and utilizes the powerful data processing capabilities of machine learning algorithms. This allows for a more comprehensive and accurate fusion of operating parameters and environmental parameters, fully leveraging the advantages of both fusion methods and improving the effectiveness of data fusion.

[0075] Physical model fusion can better adapt to changes in the physical characteristics of equipment and environment, while data-driven model fusion can automatically adjust model parameters according to changes in actual data, making the entire fusion process more adaptable and flexible, and better able to cope with various complex situations in the workshop production process.

[0076] Within the calculation unit, the regular changes in each parameter in the parameter group are calculated using the following formula: Where θ represents the air quality index of the workshop; and C i C represents the concentration of the i-th pollutant. max，i and C min，i I represents the highest and lowest concentrations of the i-th pollutant, respectively. min，i and I max，i These represent the lowest and highest air quality indices for the i-th pollutant, respectively.

[0077] In this embodiment, the formula can be used to quantitatively assess the air quality in the workshop, and the air quality index can be used to intuitively reflect the quality of the air. This makes it easier for monitoring personnel to quickly understand the air quality status of the workshop and provides a reference for environmental control and equipment maintenance during the production process.

[0078] Furthermore, the formula takes into account the concentrations of different pollutants and their corresponding highest and lowest concentration ranges, as well as the corresponding air quality index ranges. It can comprehensively assess multiple pollutants in the workshop, making it highly targeted and able to more accurately reflect the actual impact of workshop air quality on production equipment and processes.

[0079] The calculation of the regular changes of each parameter in the parameter set also includes calculations based on the following formula:

[0080] Where η represents the diffusion rate of pollutants over time;

[0081] In the formula, C represents the concentration of pollutants, t represents time, D represents the diffusion coefficient of pollutants, u represents wind speed, and S represents the source term of pollutants; Represents the Laplace operator;

[0082] In this embodiment, in real life, the air quality in the workshop affects the operation of production equipment. For example, particulate matter, dust and other impurities in the air can clog the filters and ventilation systems of the equipment, reduce the ventilation efficiency of the equipment, and affect the normal operation of the equipment. For example, in a food processing workshop, dust in the air may clog the ventilation ducts, causing the temperature and humidity in the workshop to rise, which will affect the operating efficiency of the production equipment.

[0083] Air pollutants can affect the stability of equipment, causing problems such as vibration and noise during operation. For example, in a textile workshop, airborne fiber particles may adhere to the transmission components of the equipment, leading to unstable operation, vibration, and noise.

[0084] Poor air quality can increase equipment failure rates, leading to increased downtime and reduced production efficiency. For example, in a machining workshop, dust in the air may enter the electrical control system of the equipment, causing problems such as short circuits and poor contact in electrical components, thus increasing the equipment failure rate.

[0085] Therefore, calculating the regular changes in air quality in the workshop has practical significance;

[0086] To further explain, this formula can dynamically calculate the diffusion rate of pollutants over time based on factors such as pollutant concentration, diffusion coefficient, wind speed, and source term. This provides a theoretical basis for predicting the diffusion trend of pollutants in the workshop, enabling the monitoring platform to anticipate the potential impact of pollutants on equipment and production processes and take corresponding preventive measures. Compared with simple static analysis methods, it can more accurately predict the diffusion trend and impact range of pollutants.

[0087] Based on the calculated patterns of change, predict environmental parameters that will cause a moderate impact. The prediction methods include:

[0088] The method obtains the maximum and median parameters from the parameter set, analyzes the pattern of the median parameter changing towards the maximum parameter, and, based on this pattern, obtains the difference between adjacent parameters between the median and the maximum parameter. The average difference is then calculated, and a risk threshold is preset based on this average difference. When the average difference of environmental parameters collected in future time periods exceeds the risk threshold, the operating status of the production equipment is updated to a moderately affected fault state, and the average difference is marked as a reference value. In this embodiment, the method, based on in-depth analysis of parameter change patterns, calculates the difference between adjacent parameters and the average difference, using this as the basis for setting the risk threshold. This method possesses a certain degree of scientific validity and accuracy, and can more reliably predict the degree of impact of environmental parameter changes on equipment operation.

[0089] If the operating status of the production equipment is updated to a slightly affected fault state, then the changes in operating parameters are collected based on the parameters corresponding to the slightly affected fault state. Abnormal changes in the production equipment are obtained based on the changes in operating parameters and the video of the monitored production process. If the changes in operating parameters are less than the difference between adjacent parameters obtained between the median and maximum parameters, then the update of the operating status of the production equipment to a slightly affected fault state is cancelled. In this embodiment, this mechanism allows the monitoring platform to flexibly adjust the operating status of the equipment according to the actual situation, avoiding misjudgments caused by short-term fluctuations in environmental parameters, and improving the accuracy and reliability of equipment operating status updates.

[0090] By combining changes in operating parameters with production process videos for comprehensive judgment, we can gain a more complete understanding of the actual operating status of the equipment, providing a more sufficient basis for updating the equipment's operating status, and enabling the monitoring platform to reflect the true operating conditions of the equipment more dynamically.

[0091] If the change in the operating parameter is less than the difference between adjacent parameters obtained between the median parameter and the maximum parameter, a monitoring period is preset for the change in the operating parameter. The monitoring period is preset based on the time taken for the median parameter to change to the maximum parameter, and the duration of the monitoring period is at least one-third of the time taken. During the monitoring period, if the average difference corresponding to the change in the operating parameter is half of the reference value, the operating status of the production equipment is updated to a fault state that is slightly affected.

[0092] In this embodiment, by setting reasonable monitoring periods and reference values, the updates of the device's operating status are made more reliable, avoiding frequent status updates caused by short-term parameter fluctuations, reducing the possibility of misjudgment, and improving the stability and reliability of the monitoring system.

[0093] As can be seen from the above, by setting risk thresholds and automatically updating the operating status of production equipment, this application can provide automated decision support for the production process, reduce the need for manual intervention, improve the automation level and decision-making efficiency of the production process, and make the enterprise's production management more intelligent and efficient.

[0094] This embodiment, in conjunction with the aforementioned workshop visualization monitoring platform based on digital twins, also proposes a method for applying this platform, as follows:

[0095] S10: Collect operating parameters of production equipment and environmental parameters of the workshop, and monitor the production process of the production equipment;

[0096] S20: Process operating parameters and environmental parameters, including cleaning, filtering, and format conversion of operating parameters and environmental parameters, as well as removing noisy data and outliers;

[0097] S30: The processed operating parameters and environmental parameters are fused together, and a digital twin model is constructed to analyze the correlation between changes in environmental parameters and operating parameters;

[0098] S40: Perform fusion processing on the analyzed associated impacts, including classifying the analyzed associated impacts into a tiered manner according to mild, moderate and severe impacts, and analyzing the characteristic changes of environmental parameters in different degrees of impact;

[0099] S50: Based on the analysis of environmental parameters, parameters that cause a slight impact are marked as the first environmental parameters; and a parameter group is generated based on the first environmental parameters, which includes the 10 to 15 parameters that appear most frequently, and the regular changes of each parameter in the parameter group are calculated.

[0100] S60: Update the operating status of the production equipment according to the parameter group. When the environmental parameters collected in the future period are the same as any parameter in the parameter group, the operating status of the production equipment will be updated to a fault state that is slightly affected.

[0101] In summary, by setting risk thresholds and automatically updating the operating status of production equipment, this invention can provide automated decision support for the production process, reduce the need for manual intervention, improve the automation level and decision-making efficiency of the production process, and make enterprise production management more intelligent and efficient.

[0102] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A workshop visualization monitoring platform based on digital twins, characterized in that, include: The data acquisition module includes an acquisition unit, an environmental monitoring unit, and a video surveillance unit. The acquisition unit is used to collect the operating parameters of the production equipment; The environmental monitoring unit is used to monitor the environmental parameters of the workshop; the environmental parameters include humidity, temperature and air quality; The video monitoring unit is used to monitor the production process of the production equipment. A data processing module, which responds to the data acquisition module, is used to process the operating parameters and environmental parameters; The data fusion module is used to fuse the processed operating parameters and environmental parameters, construct a digital twin model, and analyze the correlation between changes in environmental parameters and operating parameters. The LSTM network fusion processing module is used to fuse the analyzed correlation effects; the LSTM network fusion processing module includes a differentiation unit, an analysis unit, a calculation unit, and an update unit; The differentiation unit is used to classify the analyzed correlation impacts into mild, moderate and severe impacts in a stepwise manner, and to analyze the characteristic changes of the environmental parameters in different degrees of impact. The analysis unit, based on the mild impact, is used to analyze the parameters that cause the mild impact according to the environmental parameters, and to mark the parameters as first environmental parameters; And generate a parameter group based on the first environmental parameters, the parameter group including the 10 to 15 parameters that appear most frequently; The computing unit responds to the parameter set and is used to calculate the regular changes of each parameter in the parameter set; The update unit is used to update the operating status of the production equipment according to the parameter group. When the environmental parameters collected in the future period are the same as any parameter in the parameter group, the operating status of the production equipment is updated to a fault state that is slightly affected.

2. The workshop visualization monitoring platform based on digital twin as described in claim 1, characterized in that, In the data processing module, the operating parameters and environmental parameters are cleaned, filtered, and converted in format, and noise data and outliers are removed. It also includes data analysis and feature extraction of the operating parameters and environmental parameters; wherein, the data analysis includes calculating the average operating time of the production equipment, and calculating the average interval time of equipment failure based on the average operating time, and also includes the mean and variance of the environmental parameters of the workshop; Feature extraction involves using machine learning algorithms to reduce the dimensionality and extract features from the operating and environmental parameters of the generating device.

3. The workshop visualization monitoring platform based on digital twin as described in claim 1, characterized in that, In the data fusion module, the processed operating parameters and environmental parameters are fused, including fusion by means of physical model fusion, which generates the operating parameters and environmental parameters of the equipment based on the physical principles of the production equipment and the physical environment of the workshop. It also includes fusion using a data-driven model fusion approach, which uses machine learning algorithms to establish a data-driven model of the operating parameters and environmental parameters of the generating device, in order to fuse the operating parameters and environmental parameters. The machine learning algorithms include support vector machines and neural networks.

4. The workshop visualization monitoring platform based on digital twin as described in claim 1, characterized in that, In the calculation unit, the regular changes of each parameter in the parameter group are calculated according to the following formula: Where θ represents the air quality index of the workshop; In the formula, C i C represents the concentration of the i-th pollutant. max，i and C min，i I represents the highest and lowest concentrations of the i-th pollutant, respectively. min，i and I max，i These represent the lowest and highest air quality indices for the i-th pollutant, respectively.

5. The workshop visualization monitoring platform based on digital twin as described in claim 4, characterized in that, The calculation of the regular changes of each parameter in the parameter set also includes calculations based on the following formula: Where η represents the diffusion rate of pollutants over time; In the formula, C represents the concentration of pollutants, t represents time, D represents the diffusion coefficient of pollutants, u represents wind speed, and S represents the source term of pollutants; This represents the Laplace operator.

6. The workshop visualization monitoring platform based on digital twin as described in any one of claims 4 to 5, characterized in that, The environmental parameters causing the moderate impact are predicted based on the calculated regular changes. The prediction methods include: The maximum and median parameters are obtained from the parameter group. The pattern of the median parameter changing towards the maximum parameter is analyzed. Based on the pattern, the difference between adjacent parameters between the median parameter and the maximum parameter is obtained. The average difference is calculated based on the difference. A risk threshold is preset based on the average difference. When the average difference of environmental parameters collected in future time periods exceeds the risk threshold, the operating status of the production equipment is updated to a fault state with moderate impact, and the average difference is marked as a reference value.

7. The workshop visualization monitoring platform based on digital twin as described in claim 6, characterized in that, If the operating status of the production equipment is updated to a slightly affected fault state, then the changes in operating parameters are collected based on the parameters corresponding to the slightly affected fault state. Based on the changes in operating parameters and the video of the production process of the monitored production equipment, abnormal changes in the production equipment are obtained. If the changes in operating parameters are less than the difference between adjacent parameters obtained between the median parameter and the maximum parameter, then the update of the operating status of the production equipment to a slightly affected fault state is cancelled.

8. The workshop visualization monitoring platform based on digital twin as described in claim 7, characterized in that, If the change in the operating parameter is less than the difference between adjacent parameters obtained between the median parameter and the maximum parameter, a monitoring period is preset for the change in the operating parameter. The monitoring period is preset based on the time taken for the median parameter to change to the maximum parameter, and the duration of the monitoring period is at least one-third of the time taken. During the monitoring period, if the average difference corresponding to the change in the operating parameter is half of the reference value, the operating status of the production equipment is updated to a slightly affected fault state.

9. The method applied to the workshop visualization monitoring platform based on digital twins as described in claim 1, characterized in that, Includes the following steps: Collect operating parameters of production equipment and environmental parameters of the workshop, and monitor the production process of the production equipment; The operating parameters and environmental parameters are processed, including cleaning, filtering, and format conversion of the operating parameters and environmental parameters, as well as removing noise data and outliers; The processed operating parameters and environmental parameters are fused together, and a digital twin model is constructed to analyze the correlation between changes in environmental parameters and operating parameters. The analyzed associated impacts are integrated, including classifying them into mild, moderate and severe impacts in a tiered manner, and analyzing the characteristic changes of the environmental parameters in different degrees of impact. Based on the environmental parameters, the parameters that cause the slight impact are analyzed, and the parameters are marked as first environmental parameters; and a parameter group is generated based on the first environmental parameters, the parameter group including the 10 to 15 parameters that appear most frequently, and the regular changes of each parameter in the parameter group are calculated; The operating status of the production equipment is updated based on the parameter set. When the environmental parameters collected in a future time period are the same as any parameter in the parameter set, the operating status of the production equipment is updated to a fault state that is slightly affected.

Images