A method for equipment status assessment based on digital twins

Abstract

The present invention relates to the field of equipment status assessment, and discloses an equipment status assessment method based on digital twins, comprising the following steps: step one: first collect original equipment information of a raw material storage device; step two: import the collected original equipment information into a processor, the processor processes the original equipment information, and obtains an original model of the raw material storage device; step three: analyze the original equipment information, and obtain setting information of the acquisition device; step four: according to the specific content of the setting information of the acquisition device, perform acquisition device settings of the raw material storage device, after the acquisition device settings are completed, perform real-time equipment information collection, and synchronously update the collected real-time equipment information to the original model of the raw material storage device; step five: simultaneously connect the sensor device on the raw material storage device with the constructed original model of the raw material storage device. The present invention can perform a faster, more accurate and more comprehensive equipment status assessment.

Description

Technical Field

[0001] The present invention relates to the field of equipment status assessment, and in particular to an equipment status assessment method based on digital twins. Background Art

[0002] In the process of aromatic oil hydroprocessing, the feedstock tank, i.e., the feedstock storage equipment, is an important component. It is used to store the aromatic oil raw materials to be processed. The feedstock storage equipment is mainly used to store and prepare the aromatic oil raw materials to be processed. Before hydroprocessing, the raw oil needs to be stored safely and stably in the feedstock tank so that it can be smoothly transported to the hydrogenation reaction system when needed;

[0003] During the actual use of raw material storage equipment, it is necessary to conduct a status assessment on it to promptly detect whether there are any abnormalities in the raw material storage equipment. Therefore, a status assessment method will be used to conduct a status assessment on the raw material storage equipment.

[0004] The existing status assessment methods, in the process of evaluating raw material storage equipment, have low assessment accuracy and slow assessment speed, which has a certain impact on the use of status assessment methods. Therefore, an equipment status assessment method based on digital twin is proposed. Summary of the invention

[0005] The technical problem to be solved by the present invention is: how to solve the problem that in the existing status assessment method, the assessment accuracy is not high enough and the assessment speed is slow during the assessment process of raw material storage equipment, which has a certain impact on the use of the status assessment method. A device status assessment method based on digital twins is provided.

[0006] The present invention solves the above technical problems through the following technical solutions, and the present invention comprises the following steps:

[0007] Step 1: First collect the original equipment information of the raw material storage equipment;

[0008] Step 2: Importing the collected original equipment information into the processor, the processor processes the original equipment information and obtains the original model of the raw material storage equipment;

[0009] Step 3: Analyze the original device information to obtain the setting information of the acquisition device;

[0010] Step 4: According to the specific content of the setting information of the collection device, the collection device of the raw material storage device is set. After the collection device is set, real-time device information is collected, and the collected real-time device information is synchronously updated to the original model of the raw material storage device;

[0011] Step 5: At the same time, the sensor device on the raw material storage device is connected to the constructed original model of the raw material storage device, and various sensor data are uploaded to the original model of the raw material storage device in real time to obtain the real-time device model;

[0012] Step 6: The real-time equipment model is then processed and a visual model is constructed for display. At the same time, the real-time equipment model is compared with the standard model of the raw material storage equipment pre-constructed by the digital twin technology to obtain model comparison and evaluation information;

[0013] Step 7: extract the collected real-time equipment information, analyze the real-time equipment information, and obtain the external state evaluation information of the raw material storage equipment;

[0014] Step 8: Collect other information about the raw material storage equipment, analyze the other information, and obtain other evaluation information.

[0015] Furthermore, the process of establishing the original model of the raw material storage equipment is as follows:

[0016] Extract the collected original equipment information of the raw material storage equipment, import it into the digital twin modeling tool, build the model of the raw material storage equipment, and use multiple digital twin modeling tools for synchronous modeling to obtain the original models of multiple raw material storage equipment;

[0017] The original models of multiple raw material storage equipment are analyzed and compared, and the corresponding original model is selected as the original model of the raw material storage equipment finally constructed according to the comparison result.

[0018] Furthermore, the specific process of analyzing and comparing the original models of multiple raw material storage equipment and selecting the corresponding original model as the final constructed original model of the raw material storage equipment according to the comparison result is as follows:

[0019] Performing similarity comparison on the original models of the plurality of raw material storage devices to obtain the similarity between the original models of the plurality of raw material storage devices;

[0020] All similarities are extracted, and when all similarities are greater than a preset value, the original model of any raw material storage device is selected as the original model of the raw material storage device finally selected;

[0021] When the total number of similarities less than a preset value among all similarities is greater than 1 / 3 of the total number of models, that is, after removing the parts of all similarities less than the preset value, any original model of the raw material storage equipment is selected from the remaining models as the original model of the raw material storage equipment finally selected;

[0022] When the total number of similarities less than the preset value among all similarities is greater than 1 / 2 of the total number of models, the model is regenerated.

[0023] Furthermore, the setting information of the acquisition device includes a first setting type, a second setting type and a third setting type;

[0024] The specific selection process of the first setting type, the second setting type and the third setting type is as follows:

[0025] Extract the collected original device information, which includes device length, device width and device height;

[0026] When the device length, device width and device height are all greater than the preset values, the first setting type is generated;

[0027] When the device length is greater than the preset value, the device width is greater than the preset value and the device height is less than the preset value, or the device length is greater than the preset value, the device width is less than the preset value and the device height is greater than the preset value, or the device length is less than the preset value, the device width is greater than the preset value and the device height is greater than the preset value, the second setting type is generated;

[0028] When the device length, the device width, and the device height are all less than or equal to the preset values, the third setting type is generated.

[0029] Furthermore, the specific settings of the first setting type and the real-time device information collection and analysis process under the first setting type are as follows: at least eight image collection devices are set for collection. After the eight image collection devices are set, the eight image collection devices collect image information of the raw material storage device and obtain eight real-time image information. Then, the size parameters of the raw material storage device are extracted from the eight real-time image information to obtain eight real-time size parameters. Then, the eight real-time size parameters are compared for similarity. When the similarity comparison of the eight real-time size parameters is greater than a preset value, the eight real-time size parameters are exported at the same time. When the number of similarities less than the preset value in the process of the similarity comparison of the eight real-time size parameters is less than or equal to 3 but greater than 0, the remaining real-time size parameters with similarities greater than the preset value are exported. When the number of similarities less than the preset value in the process of the similarity comparison of the eight real-time size parameters is greater than 3, re-collection information is generated and sent to the image collection device, and the image information of the raw material storage device is collected again.

[0030] The specific settings of the second setting type and the real-time device information collection and analysis process under the second setting type are as follows: at least six image collection devices are set for collection. After the six image collection devices are set, the six image collection devices collect image information of the raw material storage device and obtain six real-time image information. Then, the size parameters of the raw material storage device are extracted from the six real-time image information to obtain six real-time size parameters. Then, the six real-time size parameters are compared for similarity. When the similarity comparison of the six real-time size parameters is greater than a preset value, the six real-time size parameters are exported at the same time. When the number of similarities less than the preset value in the similarity comparison process of the six real-time size parameters is less than or equal to 2 but greater than 0, the remaining real-time size parameters with similarities greater than the preset value are exported. When the number of similarities less than the preset value in the similarity comparison process of the six real-time size parameters is greater than 2, re-collection information is generated and sent to the image collection device, and the image information of the raw material storage device is collected again.

[0031] The specific settings of the third setting type and the real-time equipment information collection and analysis process under the third setting type are as follows: at least four image collection devices are set for collection. After the four image collection devices are set, the four image collection devices collect image information of the raw material storage equipment and obtain four real-time image information. Then, the size parameters of the raw material storage equipment are extracted from the four real-time image information to obtain four real-time size parameters. Then, the four real-time size parameters are compared for similarity. When the similarities obtained by the similarity comparison of the four real-time size parameters are greater than the preset value, the four real-time size parameters are exported at the same time. When any one of the similarities in the similarity comparison process of the four real-time size parameters is less than the preset value, the remaining real-time size parameters are exported at the same time. When any two of the similarities in the similarity comparison process of the four real-time size parameters are less than the preset value, re-collection information is generated and sent to the image collection device to re-collect the image information of the raw material storage equipment.

[0032] Furthermore, when uploading various sensor data to the original model of the raw material storage equipment in real time in step 5, the timeliness of the data uploaded by various sensors needs to be evaluated;

[0033] Various types of sensors include temperature sensors, pressure sensors, and liquid level sensors;

[0034] Record the time point when the temperature sensor collects the data, mark it as T1, then record the time point when the temperature data is uploaded, mark it as T2, and finally record the time point when the original model receives the data, T3;

[0035] The difference between T2 and T1 is calculated to obtain a first time difference Tt1, and the time difference between T3 and T2 is calculated to obtain a second time difference Tt2;

[0036] Record the time point when the pressure sensor collects the data, mark it as F1, then record the time point when the pressure data is uploaded, mark it as F2, and finally record the time point when the original model receives the data, F3;

[0037] The difference between F2 and F1 is calculated to obtain a first time difference Ff1, and the time difference between F3 and F2 is calculated to obtain a second time difference Ff2;

[0038] Record the time point when the liquid level sensor collects the data, mark it as E1, then record the time point when the liquid level data is uploaded, mark it as E2, and finally record the time point when the original model receives the data, E3;

[0039] The difference between E2 and E1 is calculated to obtain a first time difference Ee1, and the time difference between E3 and E2 is calculated to obtain a second time difference Ee2;

[0040] When any one of the first time difference Tt1, the second time difference Tt2, the first time difference Ff1, the second time difference Ff2, the first time difference Ee1 and the second time difference Ee2 is greater than the preset value, the evaluation information is generated;

[0041] At this time, the content of the evaluation information is that the data upload evaluation is abnormal;

[0042] When the first time difference Tt1, the second time difference Tt2, the first time difference Ff1, the second time difference Ff2, the first time difference Ee1 and the second time difference Ee2 are all less than or equal to the preset value, the evaluation information is generated;

[0043] At this time, the content of the evaluation information is that the data upload evaluation is normal.

[0044] Furthermore, the external state evaluation information of the raw material storage equipment includes a first-class evaluation, a second-class evaluation and a third-class evaluation;

[0045] The specific process of obtaining the external status evaluation information of the raw material storage equipment is as follows:

[0046] Extracting the collected real-time equipment information, the real-time equipment information is the image information of the raw material storage equipment, and obtaining clear image information after the image information of the raw material storage equipment is clarified;

[0047] The abnormal type model is preset, and then the abnormal type model is imported into the clear image information, the abnormal type model is identified from the clear image information, and then the identified abnormal type model is extracted, the identified abnormal type model is analyzed, and the abnormal evaluation parameters are obtained;

[0048] When the abnormality evaluation parameter is greater than the preset value a1, a third-category evaluation is generated; when the abnormality evaluation parameter is between the preset values ​​a1 and a2, a second-category evaluation is generated; when the abnormality evaluation parameter is less than the preset value a2, a first-category evaluation is generated, a1>a2;

[0049] The specific process of analyzing the identified anomaly type model and obtaining the anomaly assessment parameters is as follows:

[0050] Extract the identified abnormal type model, which includes rust, cracks, abnormal depressions and abnormal protrusions;

[0051] When the identified abnormal type model is rust, the rust area is collected, the rust area is scored, and a first score is obtained;

[0052] The identified abnormal type model is a crack, the crack length is collected, the crack length is scored, and a second score is obtained;

[0053] When the identified abnormal type model is an abnormal bulge, the height of the abnormal bulge is measured, and the abnormal bulge height is scored to obtain a third score;

[0054] When the identified abnormal type model is an abnormal depression, the depth of the abnormal depression is measured, and the depth of the abnormal depression is scored to obtain a fourth score;

[0055] The sum of the first score, the second score, the third score and the fourth score is calculated, that is, the abnormality assessment parameter is obtained;

[0056] The specific numerical value of the first score is proportional to the rust area, and the specific ratio is 1:1.5. The specific numerical value of the second score is proportional to the crack length, and the specific ratio is 1:1.5. The specific numerical value of the third score is proportional to the height of the abnormal protrusion, and the specific ratio is 1:2. The specific numerical value of the fourth score is proportional to the depth of the abnormal depression, and the specific ratio is 1:2.

[0057] The other assessment information includes environmental assessment information, road assessment information, abnormal equipment assessment information and warning sign assessment information;

[0058] The specific process of obtaining the other evaluation information is as follows:

[0059] Extract other collected information, including environmental information, road information, number of abnormal temperature devices and warning sign information;

[0060] Analyze environmental information to obtain environmental assessment information;

[0061] Analyze road information and obtain road assessment information;

[0062] Analyze the number of devices with abnormal temperatures and obtain evaluation information of abnormal devices;

[0063] Analyze the warning sign information and obtain warning sign evaluation information.

[0064] Furthermore, the specific process of analyzing the environmental information to obtain the environmental assessment information is as follows:

[0065] Extract the collected environmental information, which includes environmental temperature information and environmental humidity information;

[0066] When the ambient temperature information is greater than a preset value or the ambient humidity information is greater than a preset value, the environmental assessment information is generated, and the environmental assessment information is abnormal in this case;

[0067] When the ambient temperature information is less than a preset value and the ambient humidity information is less than a preset value, the environmental assessment information is generated, and the environmental assessment information indicates that the environment is normal;

[0068] The specific process of analyzing road information and obtaining road assessment information is as follows:

[0069] Extracting road information, where the road information is the width of the road for vehicles to pass within a preset range of the raw material storage equipment;

[0070] When the width of the road for vehicles to pass within the preset range of the raw material storage equipment is greater than the preset value, the road assessment information is generated, and the content of the road assessment information is that the road is normal;

[0071] When the ratio of the number of roads with a width less than a preset value to the total number of roads within the preset range of the raw material storage equipment is greater than a preset value, road assessment information is generated, and the content of the road assessment information is that the road is abnormal;

[0072] The specific process of analyzing the number of devices with abnormal temperatures and obtaining abnormal device evaluation information is as follows:

[0073] Extract the number of abnormal temperature devices collected, where the number of abnormal temperature devices is the number of other devices whose temperature is greater than a preset value within a preset range around the raw material storage device;

[0074] When the number of devices with abnormal temperature is greater than or equal to the preset value, abnormal device evaluation information is generated, and the abnormal device evaluation information is an evaluation abnormality;

[0075] When the number of devices with abnormal temperature is less than the preset value, abnormal device evaluation information is generated, and the abnormal device evaluation information is evaluated as normal;

[0076] The specific process of analyzing the warning sign information and obtaining the warning sign evaluation information is as follows:

[0077] Extracting the collected warning sign information, the warning sign information being the number of warning signs within a preset range around the raw material storage equipment;

[0078] When the number of warning signs is less than the preset value, warning sign evaluation information is generated. At this time, the specific content of the warning sign evaluation information is that the number of warning signs is abnormal;

[0079] When the number of warning signs is greater than or equal to a preset value, warning sign evaluation information is generated. At this time, the specific content of the warning sign evaluation information is that the number of warning signs is normal.

[0080] The real-time equipment model is compared with the standard model of the raw material storage equipment pre-built by the digital twin technology to obtain the model comparison evaluation information. The specific process is as follows: the real-time equipment model is compared with the standard model of the raw material storage equipment pre-built by the digital twin technology to obtain the model comparison similarity. When the model comparison similarity is greater than or equal to the preset value, the model comparison evaluation information is generated. At this time, the specific model comparison evaluation information is that the model status is normal;

[0081] When the model comparison similarity is less than the preset value, model comparison evaluation information is generated. At this time, the model comparison evaluation information specifically indicates that the model state is abnormal.

[0082] Compared with the prior art, the present invention has the following advantages: the equipment status assessment method based on digital twins collects relevant information of the raw material tank in the aromatic oil hydroprocessing process, constructs a real-time raw material storage equipment model through the digital twin technology, and then compares the constructed real-time raw material storage equipment model with the model of the raw material storage equipment under the standard state, so as to find out whether there is any abnormality in the raw material storage equipment, and conduct an immediate assessment of the uploaded sensor data to understand whether the data collected by the sensor is transmitted to the constructed raw material storage equipment model in a timely manner, thereby ensuring that the assessment of the raw material storage equipment is more accurate and faster, and also realizes the judgment of whether there is any abnormality on the outside of the raw material storage equipment in the aromatic oil hydroprocessing process through image analysis, thereby realizing another way of evaluating the raw material storage equipment, and combined with the setting of other evaluation information, a more comprehensive evaluation of the raw material storage equipment in the aromatic oil hydroprocessing process is realized, thereby being able to timely understand whether there is any abnormality in the raw material storage equipment, and realizing a more accurate and quick-read equipment status assessment, making this method more worthy of popularization and use. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] Figure 1 It is the overall flow chart of the present invention. DETAILED DESCRIPTION

[0084] The following is a detailed description of an embodiment of the present invention. This embodiment is implemented on the premise of the technical solution of the present invention, and a detailed implementation method and a specific operation process are given, but the protection scope of the present invention is not limited to the following embodiment.

[0085] like Figure 1 As shown, this embodiment provides a technical solution: a device status assessment method based on digital twins, comprising the following steps:

[0086] Step 1: First collect the original equipment information of the raw material storage equipment;

[0087] Step 2: Importing the collected original equipment information into the processor, the processor processes the original equipment information and obtains the original model of the raw material storage equipment;

[0088] Step 3: Analyze the original device information to obtain the setting information of the acquisition device;

[0089] Step 4: According to the specific content of the setting information of the collection device, the collection device of the raw material storage device is set. After the collection device is set, real-time device information is collected, and the collected real-time device information is synchronously updated to the original model of the raw material storage device;

[0090] Step 5: At the same time, the sensor device on the raw material storage device is connected to the constructed original model of the raw material storage device, and various sensor data are uploaded to the original model of the raw material storage device in real time to obtain the real-time device model;

[0091] Step 6: The real-time equipment model is then processed and a visual model is constructed for display. At the same time, the real-time equipment model is compared with the standard model of the raw material storage equipment pre-constructed by the digital twin technology to obtain model comparison and evaluation information;

[0092] Step 7: extract the collected real-time equipment information, analyze the real-time equipment information, and obtain the external state evaluation information of the raw material storage equipment;

[0093] Step 8: Collect other information about the raw material storage equipment, analyze the other information, and obtain other evaluation information;

[0094] The present invention collects relevant information of the raw material tank in the aromatic oil hydrogenation processing process, constructs a real-time raw material storage equipment model through the digital twin technology, and then compares the constructed real-time raw material storage equipment model with the model of the raw material storage equipment under the standard state. It can not only find out whether there is any abnormality in the raw material storage equipment, but also conduct a real-time evaluation of the uploaded sensor data to understand whether the data collected by the sensor is transmitted to the constructed raw material storage equipment model in time, thereby ensuring that the evaluation of the raw material storage equipment is more accurate and faster, and also realizes the judgment of whether there is any abnormality on the outside of the raw material storage equipment in the aromatic oil hydrogenation processing process through image analysis, thereby realizing another way of evaluating the raw material storage equipment. Combined with the setting of other evaluation information, a more comprehensive evaluation of the raw material storage equipment in the aromatic oil hydrogenation processing process is realized, thereby being able to timely understand whether there is any abnormality in the raw material storage equipment.

[0095] The process of establishing the original model of the raw material storage equipment is as follows:

[0096] Extract the collected original equipment information of the raw material storage equipment, import it into the digital twin modeling tool, build the model of the raw material storage equipment, and use multiple digital twin modeling tools for synchronous modeling to obtain the original models of multiple raw material storage equipment;

[0097] Analyze and compare the original models of multiple raw material storage equipment, and select the corresponding original model as the original model of the raw material storage equipment finally constructed according to the comparison result;

[0098] Through the above process, a high-precision and high-reliability digital twin model of the raw material tank can be constructed, providing strong support for the company's production management.

[0099] The specific process of analyzing and comparing the original models of multiple raw material storage equipment and selecting the corresponding original model as the final constructed original model of the raw material storage equipment according to the comparison results is as follows:

[0100] Performing similarity comparison on the original models of the plurality of raw material storage devices to obtain the similarity between the original models of the plurality of raw material storage devices;

[0101] All similarities are extracted, and when all similarities are greater than a preset value, the original model of any raw material storage device is selected as the original model of the raw material storage device finally selected;

[0102] When the total number of similarities less than a preset value among all similarities is greater than 1 / 3 of the total number of models, that is, after removing the parts of all similarities less than the preset value, any original model of the raw material storage equipment is selected from the remaining models as the original model of the raw material storage equipment finally selected;

[0103] When the total number of similarities less than the preset value is greater than 1 / 2 of the total number of models, the model is regenerated;

[0104] The above process improves the accuracy and reliability of the model. Different modeling tools may build models based on different algorithms, assumptions, and focuses. Through the simultaneous modeling of multiple tools, the accuracy and reliability of the model can be verified from different angles, reducing the deviation that may be caused by a single tool. By comparing and analyzing multiple models, the advantages and disadvantages of each model can be comprehensively evaluated, so as to select the model that best meets the actual needs.

[0105] Enhance the adaptability and flexibility of the model. Having multiple models means more options to choose from during the decision-making process. This helps to select the most appropriate model in different scenarios, improve the flexibility and adaptability of decision-making, and in the process of model selection, rapid iteration and optimization can be performed based on the feedback of multiple models to improve modeling efficiency and effectiveness.

[0106] The setting information of the acquisition device includes a first setting type, a second setting type and a third setting type;

[0107] The specific selection process of the first setting type, the second setting type and the third setting type is as follows:

[0108] Extract the collected original device information, including device length, device width and device height;

[0109] When the device length, device width and device height are all greater than the preset values, the first setting type is generated;

[0110] When the device length is greater than the preset value, the device width is greater than the preset value and the device height is less than the preset value, or the device length is greater than the preset value, the device width is less than the preset value and the device height is greater than the preset value, or the device length is less than the preset value, the device width is greater than the preset value and the device height is greater than the preset value, the second setting type is generated;

[0111] When the device length, device width and device height are all less than or equal to the preset value, the third setting type is generated;

[0112] Through the setting of the above process, different numbers of image acquisition devices can be set according to the different sizes of raw material tanks in the actual aromatic oil hydrogenation process to collect the size information of the raw material tanks, that is, the raw material storage equipment, etc., to ensure that more data support can be obtained in the subsequent modeling process, thereby improving the final modeling accuracy.

[0113] The specific settings of the first setting type and the real-time device information collection and analysis process under the first setting type are as follows: at least eight image collection devices are set for collection. After the eight image collection devices are set, the eight image collection devices collect image information of the raw material storage device and obtain eight real-time image information. Then, the size parameters of the raw material storage device are extracted from the eight real-time image information to obtain eight real-time size parameters. Then, the eight real-time size parameters are compared for similarity. When the similarity comparison of the eight real-time size parameters is greater than the preset value, the eight real-time size parameters are exported at the same time. When the number of similarities less than the preset value in the process of the similarity comparison of the eight real-time size parameters is less than or equal to 3 but greater than 0, the remaining real-time size parameters with similarities greater than the preset value are exported. When the number of similarities less than the preset value in the process of the similarity comparison of the eight real-time size parameters is greater than 3, re-collection information is generated and sent to the image collection device, and the image information of the raw material storage device is collected again.

[0114] The specific settings of the second setting type and the real-time device information collection and analysis process under the second setting type are as follows: at least six image collection devices are set for collection. After the six image collection devices are set, the six image collection devices collect image information of the raw material storage device and obtain six real-time image information. Then, the size parameters of the raw material storage device are extracted from the six real-time image information to obtain six real-time size parameters. Then, the six real-time size parameters are compared for similarity. When the similarity comparison of the six real-time size parameters is greater than a preset value, the six real-time size parameters are exported at the same time. When the number of similarities less than the preset value in the similarity comparison process of the six real-time size parameters is less than or equal to 2 but greater than 0, the remaining real-time size parameters with similarities greater than the preset value are exported. When the number of similarities less than the preset value in the similarity comparison process of the six real-time size parameters is greater than 2, re-collection information is generated and sent to the image collection device, and the image information of the raw material storage device is collected again.

[0115] The specific settings of the third setting type and the real-time device information collection and analysis process under the third setting type are as follows: at least four image collection devices are set for collection. After the four image collection devices are set, the four image collection devices collect image information of the raw material storage device to obtain four real-time image information, and then extract the size parameters of the raw material storage device from the four real-time image information to obtain four real-time size parameters. Then, the four real-time size parameters are compared for similarity. When the similarities obtained by the similarity comparison of the four real-time size parameters are greater than a preset value, the four real-time size parameters are exported at the same time. When any one of the similarities in the similarity comparison process of the four real-time size parameters is less than a preset value, the remaining real-time size parameters are exported at the same time. When any two of the similarities in the similarity comparison process of the four real-time size parameters are less than a preset value, re-collection information is generated and sent to the image collection device, and the image information of the raw material storage device is collected again.

[0116] Through the above process, relevant analysis is performed on the image information collected by image acquisition devices set up under different types to ensure the accuracy of the final collected image data.

[0117] When uploading various sensor data to the original model of the raw material storage equipment in real time in step 5, it is necessary to evaluate the immediacy of the data uploaded by various sensors;

[0118] Various types of sensors include temperature sensors, pressure sensors, and liquid level sensors;

[0119] Record the time point when the temperature sensor collects the data, mark it as T1, then record the time point when the temperature data is uploaded, mark it as T2, and finally record the time point when the original model receives the data, T3;

[0120] The difference between T2 and T1 is calculated to obtain a first time difference Tt1, and the time difference between T3 and T2 is calculated to obtain a second time difference Tt2;

[0121] Record the time point when the pressure sensor collects the data, mark it as F1, then record the time point when the pressure data is uploaded, mark it as F2, and finally record the time point when the original model receives the data, F3;

[0122] The difference between F2 and F1 is calculated to obtain a first time difference Ff1, and the time difference between F3 and F2 is calculated to obtain a second time difference Ff2;

[0123] Record the time point when the liquid level sensor collects the data, mark it as E1, then record the time point when the liquid level data is uploaded, mark it as E2, and finally record the time point when the original model receives the data, E3;

[0124] The difference between E2 and E1 is calculated to obtain a first time difference Ee1, and the time difference between E3 and E2 is calculated to obtain a second time difference Ee2;

[0125] When any one of the first time difference Tt1, the second time difference Tt2, the first time difference Ff1, the second time difference Ff2, the first time difference Ee1 and the second time difference Ee2 is greater than the preset value, the evaluation information is generated;

[0126] At this time, the content of the evaluation information is that the data upload evaluation is abnormal;

[0127] When the first time difference Tt1, the second time difference Tt2, the first time difference Ff1, the second time difference Ff2, the first time difference Ee1 and the second time difference Ee2 are all less than or equal to the preset value, the evaluation information is generated;

[0128] At this time, the content of the evaluation information is that the data upload evaluation is normal;

[0129] Through the above process, the analysis of the time difference of sensor data transmission is realized, and whether there is a large delay in data transmission is discovered in time, which reduces the situation where the data transmission delay is too long and causes errors in the comparison results of the established model.

[0130] The external status assessment information of the raw material storage equipment includes a first-class assessment, a second-class assessment and a third-class assessment;

[0131] The specific process of obtaining the external status evaluation information of the raw material storage equipment is as follows:

[0132] Extracting the collected real-time equipment information, the real-time equipment information is the image information of the raw material storage equipment, and obtaining clear image information after the image information of the raw material storage equipment is clarified;

[0133] The abnormal type model is preset, and then the abnormal type model is imported into the clear image information, the abnormal type model is identified from the clear image information, and then the identified abnormal type model is extracted, the identified abnormal type model is analyzed, and the abnormal evaluation parameters are obtained;

[0134] When the abnormality assessment parameter is greater than the preset value a1, a third-category assessment is generated; when the abnormality assessment parameter is between the preset values ​​a1 and a2, a second-category assessment is generated; and when the abnormality assessment parameter is less than the preset value a2, a first-category assessment is generated;

[0135] The specific process of analyzing the identified anomaly type model and obtaining the anomaly assessment parameters is as follows:

[0136] Extract the identified abnormal type model, which includes rust, cracks, abnormal depressions and abnormal protrusions;

[0137] When the identified abnormal type model is rust, the rust area is collected, the rust area is scored, and a first score is obtained;

[0138] The identified abnormal type model is a crack, the crack length is collected, the crack length is scored, and a second score is obtained;

[0139] When the identified abnormal type model is an abnormal bulge, the height of the abnormal bulge is measured, and the abnormal bulge height is scored to obtain a third score;

[0140] When the identified abnormal type model is an abnormal depression, the depth of the abnormal depression is measured, and the depth of the abnormal depression is scored to obtain a fourth score;

[0141] The sum of the first score, the second score, the third score and the fourth score is calculated, that is, the abnormality assessment parameter is obtained;

[0142] The specific numerical value of the first score is proportional to the corrosion area, the specific numerical value of the second score is proportional to the crack length, the specific numerical value of the third score is proportional to the height of the abnormal protrusion, and the specific numerical value of the fourth score is proportional to the depth of the abnormal depression;

[0143] Through the above process, the image information of the raw material tank in the process of aromatic oil hydroprocessing collected by the acquisition equipment is more fully utilized. At the same time, the image information is analyzed, that is, the external state of the raw material tank in the process of aromatic oil hydroprocessing is evaluated, which can timely discover safety hazards and prevent accidents. Through image analysis, safety hazards such as rust and cracks on the surface of the raw material tank can be discovered in time. If these hidden dangers are not discovered and handled in time, they may cause raw material leakage, equipment damage and even safety accidents. Timely discovery and handling of these hidden dangers will help prevent accidents and ensure production safety.

[0144] Optimize equipment management. Image analysis can provide detailed information about the surface of the raw material tank, including the degree of rust, crack location and size, etc. This information helps to formulate an accurate maintenance plan to avoid over-maintenance or under-maintenance. At the same time, according to the image analysis results, the maintenance time and content can be reasonably arranged to improve the efficiency of equipment management.

[0145] Extend equipment life: Timely detection and treatment of problems such as rust and cracks can effectively prevent these problems from further deteriorating, thereby extending the service life of the raw material tank. This helps reduce equipment replacement costs and improve production efficiency.

[0146] To ensure the quality of raw materials, the integrity of the raw material tank is the premise of ensuring the quality of raw materials. Through image analysis, we can ensure that the raw material tank is free of rust, cracks and other problems, which helps to prevent the raw materials from being contaminated or damaged during storage, thereby ensuring the quality of raw materials and improving product quality.

[0147] The other assessment information includes environmental assessment information, road assessment information, abnormal equipment assessment information and warning sign assessment information;

[0148] The specific process of obtaining the other evaluation information is as follows:

[0149] Extract other collected information, including environmental information, road information, number of abnormal temperature devices and warning sign information;

[0150] Analyze environmental information to obtain environmental assessment information;

[0151] Analyze road information and obtain road assessment information;

[0152] Analyze the number of devices with abnormal temperatures and obtain evaluation information of abnormal devices;

[0153] Analyze the warning sign information and obtain warning sign evaluation information.

[0154] The specific process of analyzing the environmental information to obtain the environmental assessment information is as follows:

[0155] Extract the collected environmental information, which includes environmental temperature information and environmental humidity information;

[0156] When the ambient temperature information is greater than a preset value or the ambient humidity information is greater than a preset value, the environmental assessment information is generated, and the environmental assessment information is abnormal in this case;

[0157] When the ambient temperature information is less than a preset value and the ambient humidity information is less than a preset value, the environmental assessment information is generated, and the environmental assessment information indicates that the environment is normal;

[0158] Too high an ambient temperature may cause the raw materials to volatilize, decompose or deteriorate, thus affecting the effect of the hydrogenation reaction and the quality of the product. At the same time, too low a temperature may affect the fluidity of the raw materials and increase the difficulty of processing. Therefore, in the environmental assessment, it is necessary to pay attention to the thermal insulation performance of the raw material tank, the stability and accuracy of the temperature control system, and the temperature adjustment ability to cope with emergencies;

[0159] The impact of ambient humidity on the aromatic oil hydroprocessing process is relatively small, but it cannot be ignored. A high humidity environment may cause condensation on the surface of raw material tanks, pipelines and other equipment, increase the risk of corrosion, and affect the safety and service life of the equipment. In addition, excessive humidity may also affect the purity of the raw materials, thereby affecting the quality of the product;

[0160] The specific process of analyzing road information and obtaining road assessment information is as follows:

[0161] Extracting road information, where the road information is the width of the road for vehicles to pass within a preset range of the raw material storage equipment;

[0162] When the width of the road for vehicles to pass within the preset range of the raw material storage equipment is greater than the preset value, the road assessment information is generated, and the content of the road assessment information is that the road is normal;

[0163] When the ratio of the number of roads with a width less than a preset value to the total number of roads within the preset range of the raw material storage equipment is greater than a preset value, road assessment information is generated, and the content of the road assessment information is that the road is abnormal;

[0164] By evaluating the road status, we can know whether there are any abnormalities on the road. Reasonable planning of the road width around the raw material tank can ensure the safe passage of transport vehicles (such as oil tankers, maintenance vehicles, etc.) and avoid traffic accidents or transportation delays caused by narrow roads. Sufficiently wide roads can also ensure that vehicles can quickly evacuate or perform emergency operations in emergency situations (such as fire, leakage, etc.), reducing accident losses. In the event of an emergency, such as a fire or leakage, emergency vehicles such as fire trucks and ambulances need to arrive at the scene quickly. The rationality of the road width around the raw material tank directly affects the speed and response efficiency of these vehicles. Wide roads can ensure that emergency vehicles arrive smoothly and carry out rescue work, thereby minimizing the harm of accidents to people and the environment.

[0165] The specific process of analyzing the number of devices with abnormal temperatures and obtaining abnormal device evaluation information is as follows:

[0166] Extract the number of abnormal temperature devices collected, where the number of abnormal temperature devices is the number of other devices whose temperature is greater than a preset value within a preset range around the raw material storage device;

[0167] When the number of devices with abnormal temperature is greater than or equal to the preset value, abnormal device evaluation information is generated, and the abnormal device evaluation information is an evaluation abnormality;

[0168] When the number of devices with abnormal temperature is less than the preset value, abnormal device evaluation information is generated, and the abnormal device evaluation information is evaluated as normal;

[0169] Abnormal temperature equipment refers to equipment whose operating temperature is greater than the preset value. Analyzing abnormal temperature equipment can identify potential thermal risks. High-temperature equipment around the raw material tank may generate a large amount of heat and radiation, posing a potential thermal risk to the raw material tank and the aromatic oil stored inside it. By analyzing the number of high-temperature equipment, the potential impact of these equipment on the raw material tank can be evaluated, so as to take corresponding preventive measures. The safe distance between high-temperature equipment and the raw material tank is one of the key factors to ensure safety. By analyzing the number of high-temperature equipment, the equipment layout can be reasonably planned to ensure that the safe distance meets relevant standards and specifications, reduce safety hazards caused by thermal radiation, heat conduction, etc., and understand the number and distribution of high-temperature equipment around the raw material tank, which is helpful to formulate targeted emergency plans. In the event of an emergency such as a high-temperature equipment failure or fire, it can be quickly located and appropriate emergency measures can be taken to reduce accident losses.

[0170] The specific process of analyzing the warning sign information and obtaining the warning sign evaluation information is as follows:

[0171] Extracting the collected warning sign information, the warning sign information being the number of warning signs within a preset range around the raw material storage equipment;

[0172] When the number of warning signs is less than the preset value, warning sign evaluation information is generated. At this time, the specific content of the warning sign evaluation information is that the number of warning signs is abnormal;

[0173] When the number of warning signs is greater than or equal to the preset value, warning sign evaluation information is generated. At this time, the specific content of the warning sign evaluation information is that the number of warning signs is normal;

[0174] The above assessment can improve safety awareness and prevention capabilities. Warning signs can clearly indicate the dangers of the raw material tank and its surrounding areas, allowing workers and outsiders to quickly identify and stay away from potential sources of danger. This helps reduce safety accidents caused by ignorance of dangerous areas. Eye-catching warning signs can attract people's attention and concern, and enhance their safety awareness and vigilance. When facing potential dangers, people can operate more carefully, thereby reducing the probability of accidents.

[0175] The real-time equipment model is compared with the standard model of the raw material storage equipment pre-built by the digital twin technology to obtain the model comparison evaluation information. The specific process is as follows: the real-time equipment model is compared with the standard model of the raw material storage equipment pre-built by the digital twin technology to obtain the model comparison similarity. When the model comparison similarity is greater than or equal to the preset value, the model comparison evaluation information is generated. At this time, the specific model comparison evaluation information is that the model status is normal;

[0176] When the model comparison similarity is less than the preset value, model comparison evaluation information is generated. At this time, the model comparison evaluation information specifically indicates that the model state is abnormal.

[0177] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first" and "second" may explicitly or implicitly include at least one of the features. In the description of the present invention, the meaning of "plurality" is at least two, such as two, three, etc., unless otherwise clearly and specifically defined.

[0178] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, without contradiction.

[0179] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations of the present invention. A person skilled in the art may change, modify, replace and vary the above embodiments within the scope of the present invention.

Claims

1. A device status assessment method based on digital twins, characterized in that: The following steps are involved: Step 1: First collect the original equipment information of the raw material storage equipment; Step 2: Importing the collected original equipment information into the processor, the processor processes the original equipment information and obtains the original model of the raw material storage equipment; Step 3: Analyze the original device information to obtain the setting information of the acquisition device; Step 4: According to the specific content of the setting information of the collection device, the collection device of the raw material storage device is set. After the collection device is set, real-time device information is collected, and the collected real-time device information is synchronously updated to the original model of the raw material storage device; Step 5: At the same time, the sensor device on the raw material storage device is connected to the constructed original model of the raw material storage device, and various sensor data are uploaded to the original model of the raw material storage device in real time to obtain the real-time device model; Step 6: The real-time equipment model is then processed and a visual model is constructed for display. At the same time, the real-time equipment model is compared with the standard model of the raw material storage equipment pre-constructed by the digital twin technology to obtain model comparison and evaluation information; Step 7: extract the collected real-time equipment information, analyze the real-time equipment information, and obtain the external state evaluation information of the raw material storage equipment; Step 8: Collect other information about the raw material storage equipment, analyze the other information, and obtain other evaluation information; The process of establishing the original model of the raw material storage equipment is as follows: Extract the collected original equipment information of the raw material storage equipment, import it into the digital twin modeling tool, build the model of the raw material storage equipment, and use multiple digital twin modeling tools for synchronous modeling to obtain the original models of multiple raw material storage equipment; Analyze and compare the original models of multiple raw material storage equipment, and select the corresponding original model as the original model of the raw material storage equipment finally constructed according to the comparison result; The specific process of analyzing and comparing the original models of multiple raw material storage equipment and selecting the corresponding original model as the final constructed original model of the raw material storage equipment according to the comparison results is as follows: Performing similarity comparison on the original models of the plurality of raw material storage devices to obtain the similarity between the original models of the plurality of raw material storage devices; All similarities are extracted, and when all similarities are greater than a preset value, the original model of any raw material storage device is selected as the original model of the raw material storage device finally selected; When the total number of similarities less than a preset value among all similarities is greater than 1 / 3 of the total number of models, that is, after removing the parts of all similarities less than the preset value, any original model of the raw material storage equipment is selected from the remaining models as the original model of the raw material storage equipment finally selected; When the total number of similarities less than the preset value is greater than 1 / 2 of the total number of models, the model is regenerated; The setting information of the acquisition device includes a first setting type, a second setting type and a third setting type; The specific selection process of the first setting type, the second setting type and the third setting type is as follows: Extract the collected original device information, which includes device length, device width and device height; When the device length, device width and device height are all greater than the preset values, the first setting type is generated; When the device length is greater than the preset value, the device width is greater than the preset value and the device height is less than the preset value, or the device length is greater than the preset value, the device width is less than the preset value and the device height is greater than the preset value, or the device length is less than the preset value, the device width is greater than the preset value and the device height is greater than the preset value, the second setting type is generated; When the device length, device width and device height are all less than or equal to the preset value, the third setting type is generated; The specific settings of the first setting type and the real-time device information collection and analysis process under the first setting type are as follows: at least eight image collection devices are set for collection. After the eight image collection devices are set, the eight image collection devices collect image information of the raw material storage device and obtain eight real-time image information. Then, the size parameters of the raw material storage device are extracted from the eight real-time image information to obtain eight real-time size parameters. Then, the eight real-time size parameters are compared for similarity. When the similarity comparison of the eight real-time size parameters is greater than the preset value, the eight real-time size parameters are exported at the same time. When the number of similarities less than the preset value in the process of the similarity comparison of the eight real-time size parameters is less than or equal to 3 but greater than 0, the remaining real-time size parameters with similarities greater than the preset value are exported. When the number of similarities less than the preset value in the process of the similarity comparison of the eight real-time size parameters is greater than 3, re-collection information is generated and sent to the image collection device, and the image information of the raw material storage device is collected again. The specific settings of the second setting type and the real-time device information collection and analysis process under the second setting type are as follows: at least six image collection devices are set for collection. After the six image collection devices are set, the six image collection devices collect image information of the raw material storage device and obtain six real-time image information. Then, the size parameters of the raw material storage device are extracted from the six real-time image information to obtain six real-time size parameters. Then, the six real-time size parameters are compared for similarity. When the similarity comparison of the six real-time size parameters is greater than a preset value, the six real-time size parameters are exported at the same time. When the number of similarities less than the preset value in the similarity comparison process of the six real-time size parameters is less than or equal to 2 but greater than 0, the remaining real-time size parameters with similarities greater than the preset value are exported. When the number of similarities less than the preset value in the similarity comparison process of the six real-time size parameters is greater than 2, re-collection information is generated and sent to the image collection device, and the image information of the raw material storage device is collected again. The specific settings of the third setting type and the real-time equipment information collection and analysis process under the third setting type are as follows: at least four image collection devices are set for collection. After the four image collection devices are set, the four image collection devices collect image information of the raw material storage equipment and obtain four real-time image information. Then, the size parameters of the raw material storage equipment are extracted from the four real-time image information to obtain four real-time size parameters. Then, the four real-time size parameters are compared for similarity. When the similarities obtained by the similarity comparison of the four real-time size parameters are greater than the preset value, the four real-time size parameters are exported at the same time. When any one of the similarities in the similarity comparison process of the four real-time size parameters is less than the preset value, the remaining real-time size parameters are exported at the same time. When any two of the similarities in the similarity comparison process of the four real-time size parameters are less than the preset value, re-collection information is generated and sent to the image collection device to re-collect the image information of the raw material storage equipment.

2. According to claim 1, a method for evaluating equipment status based on digital twins is characterized in that: When uploading various sensor data to the original model of the raw material storage equipment in real time in step 5, it is necessary to evaluate the immediacy of the data uploaded by various sensors; Various types of sensors include temperature sensors, pressure sensors, and liquid level sensors; Record the time point when the temperature sensor collects the data, mark it as T1, then record the time point when the temperature data is uploaded, mark it as T2, and finally record the time point when the original model receives the data, T3; The difference between T2 and T1 is calculated to obtain a first time difference Tt1, and the time difference between T3 and T2 is calculated to obtain a second time difference Tt2; Record the time point when the pressure sensor collects the data, mark it as F1, then record the time point when the pressure data is uploaded, mark it as F2, and finally record the time point when the original model receives the data, F3; The difference between F2 and F1 is calculated to obtain a first time difference Ff1, and the time difference between F3 and F2 is calculated to obtain a second time difference Ff2; Record the time point when the liquid level sensor collects the data, mark it as E1, then record the time point when the liquid level data is uploaded, mark it as E2, and finally record the time point when the original model receives the data, E3; The difference between E2 and E1 is calculated to obtain a first time difference Ee1, and the time difference between E3 and E2 is calculated to obtain a second time difference Ee2; When any one of the first time difference Tt1, the second time difference Tt2, the first time difference Ff1, the second time difference Ff2, the first time difference Ee1 and the second time difference Ee2 is greater than the preset value, the evaluation information is generated; At this time, the content of the evaluation information is that the data upload evaluation is abnormal; When the first time difference Tt1, the second time difference Tt2, the first time difference Ff1, the second time difference Ff2, the first time difference Ee1 and the second time difference Ee2 are all less than or equal to the preset value, the evaluation information is generated; At this time, the content of the evaluation information is that the data upload evaluation is normal.

3. The device status assessment method based on digital twin according to claim 1 is characterized in that: The external status assessment information of the raw material storage equipment includes a first-class assessment, a second-class assessment and a third-class assessment; The specific process of obtaining the external status evaluation information of the raw material storage equipment is as follows: Extracting the collected real-time equipment information, the real-time equipment information is the image information of the raw material storage equipment, and obtaining clear image information after the image information of the raw material storage equipment is clarified; The abnormal type model is preset, and then the abnormal type model is imported into the clear image information, the abnormal type model is identified from the clear image information, and then the identified abnormal type model is extracted, the identified abnormal type model is analyzed, and the abnormal evaluation parameters are obtained; When the abnormality assessment parameter is greater than the preset value a1, a third-category assessment is generated; when the abnormality assessment parameter is between the preset values ​​a1 and a2, a second-category assessment is generated; and when the abnormality assessment parameter is less than the preset value a2, a first-category assessment is generated; The specific process of analyzing the identified anomaly type model and obtaining the anomaly assessment parameters is as follows: Extract the identified abnormal type model, which includes rust, cracks, abnormal depressions and abnormal protrusions; When the identified abnormal type model is rust, the rust area is collected, the rust area is scored, and a first score is obtained; The identified abnormal type model is a crack, the crack length is collected, the crack length is scored, and a second score is obtained; When the identified abnormal type model is an abnormal bulge, the height of the abnormal bulge is measured, and the abnormal bulge height is scored to obtain a third score; When the identified abnormal type model is an abnormal depression, the depth of the abnormal depression is measured, and the depth of the abnormal depression is scored to obtain a fourth score; The sum of the first score, the second score, the third score and the fourth score is calculated, that is, the abnormality assessment parameter is obtained; The specific numerical value of the first score is proportional to the rust area, the specific numerical value of the second score is proportional to the crack length, the specific numerical value of the third score is proportional to the height of the abnormal protrusion, and the specific numerical value of the fourth score is proportional to the depth of the abnormal depression.

4. The device status assessment method based on digital twin according to claim 1 is characterized in that: The other assessment information includes environmental assessment information, road assessment information, abnormal equipment assessment information and warning sign assessment information; The specific process of obtaining the other evaluation information is as follows: Extract other collected information, including environmental information, road information, number of abnormal temperature devices and warning sign information; Analyze environmental information to obtain environmental assessment information; Analyze road information and obtain road assessment information; Analyze the number of devices with abnormal temperatures and obtain evaluation information of abnormal devices; Analyze the warning sign information and obtain warning sign evaluation information.

5. The device status assessment method based on digital twin according to claim 4 is characterized in that: The specific process of analyzing the environmental information to obtain the environmental assessment information is as follows: Extract the collected environmental information, which includes environmental temperature information and environmental humidity information; When the ambient temperature information is greater than a preset value or the ambient humidity information is greater than a preset value, the environmental assessment information is generated, and the environmental assessment information is abnormal in this case; When the ambient temperature information is less than a preset value and the ambient humidity information is less than a preset value, the environmental assessment information is generated, and the environmental assessment information indicates that the environment is normal; The specific process of analyzing road information and obtaining road assessment information is as follows: Extracting road information, where the road information is the width of the road for vehicles to pass within a preset range of the raw material storage equipment; When the width of the road for vehicles to pass within the preset range of the raw material storage equipment is greater than the preset value, the road assessment information is generated, and the content of the road assessment information is that the road is normal; When the ratio of the number of roads with a width less than a preset value to the total number of roads within the preset range of the raw material storage equipment is greater than a preset value, road assessment information is generated, and the content of the road assessment information is that the road is abnormal; The specific process of analyzing the number of devices with abnormal temperatures and obtaining abnormal device evaluation information is as follows: Extract the number of abnormal temperature devices collected, where the number of abnormal temperature devices is the number of other devices whose temperature is greater than a preset value within a preset range around the raw material storage device; When the number of devices with abnormal temperature is greater than or equal to the preset value, abnormal device evaluation information is generated, and the abnormal device evaluation information is an evaluation abnormality; When the number of devices with abnormal temperature is less than the preset value, abnormal device evaluation information is generated, and the abnormal device evaluation information is evaluated as normal; The specific process of analyzing the warning sign information and obtaining the warning sign evaluation information is as follows: Extracting the collected warning sign information, the warning sign information being the number of warning signs within a preset range around the raw material storage equipment; When the number of warning signs is less than the preset value, warning sign evaluation information is generated. At this time, the specific content of the warning sign evaluation information is that the number of warning signs is abnormal; When the number of warning signs is greater than or equal to a preset value, warning sign evaluation information is generated. At this time, the specific content of the warning sign evaluation information is that the number of warning signs is normal.

Images