Beam field accident early warning method and system based on Internet of Things, medium and electronic equipment

Abstract

The invention discloses a beam field accident early warning method and system based on the Internet of Things, a medium and electronic equipment. Relates to the technical field of beam field accident early warning. Acquiring real-time data and historical data of different accident types of the target beam field; performing first early warning and second early warning based on the real-time data and the historical data; the second early warning is to obtain a real-time risk level corresponding to each accident type according to the real-time data; when the real-time risk level exceeds a risk level threshold value, generating early warning information based on the real-time data; otherwise, potential risks are obtained according to historical data, and early warning information is generated based on the potential risks; according to the scheme, the accident risk in the beam field is judged according to the fact data, and meanwhile, the potential risk type of the accident risk is predicted and analyzed according to the historical accident information, so that the comprehensiveness of early warning is improved, the accuracy of early warning is improved, workers or related equipment can conveniently process the accident risk in the beam field in advance, and the working efficiency is improved. And the possibility of accidents is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of beam yard accident early warning technology, and in particular to a beam yard accident early warning method, system, medium and electronic equipment based on the Internet of Things. Background Art

[0002] A beam yard is a workplace or facility dedicated to the fabrication and production of precast concrete beams. In construction and infrastructure projects, a beam yard is typically a dedicated production area used to manufacture concrete beams of various types and sizes to meet project needs.

[0003] With the rapid development of social economy, the construction industry has also made great progress. Various buildings have sprung up, so the demand for prefabricated beams has become increasingly greater. With the continuous development of beam yards, various beam yard accidents have also followed one after another. This not only reduces the production efficiency of the beam yard, but also has a great impact on people’s lives and property safety.

[0004] In order to reduce the safety risks of beam yards, more and more people will set up relevant monitoring systems in the beam yards. Once an accident occurs in the beam yard, the monitoring system will alarm in time. However, even if the monitoring system alarms immediately after a failure occurs, it can only minimize the losses as much as possible but cannot reduce the possibility of accidents. Summary of the Invention

[0005] The technical problem to be solved by the present invention is that the traditional beam yard monitoring system can alarm as soon as a fault occurs, but it has the disadvantage of not being able to reduce the possibility of accidents. The purpose of the present invention is to provide a beam yard accident early warning method, system, medium and electronic equipment based on the Internet of Things. While judging the accident risk in the beam yard based on factual data, it also predicts and analyzes the potential risk types of accident risks based on historical accident information, which not only improves the comprehensiveness of the early warning, but also improves the accuracy of the early warning, making it convenient for staff or related equipment to deal with the accident risks in the beam yard in advance and reduce the possibility of accidents.

[0006] The present invention is achieved through the following technical solutions:

[0007] This solution provides an IoT-based beam yard accident early warning method, including:

[0008] Collect real-time and historical data of different accident types in the target beam yard;

[0009] Performing a first warning based on real-time data and historical data; the first warning includes performing a data source warning based on real-time data and historical data;

[0010] Second warning based on real-time and historical data: obtain the real-time risk level corresponding to each accident type based on real-time data;

[0011] A preset risk level threshold is used to determine whether the real-time risk level exceeds the risk level threshold. If so, an early warning message is generated based on the real-time data; otherwise, potential risks are obtained based on historical data, and an early warning message is generated based on the potential risks.

[0012] A further optimization scheme is that the first warning based on real-time data and historical data includes the following methods:

[0013] Determine whether real-time and historical data exist for different accident types:

[0014] If there is no real-time data or historical data for the current accident type, then an early warning message is generated based on the current accident type;

[0015] If there is no real-time data for the current accident type, but there is historical data, the warning information is determined based on the abnormal conditions of the historical data;

[0016] If there is real-time data for the current accident type but no historical data, the warning information will be determined based on the hazard source monitoring time.

[0017] A further optimization scheme is to determine the warning information based on the abnormal conditions of historical data; including the following method:

[0018] Determine whether the historical data is abnormal data. If so, generate early warning information based on the current accident type and abnormal data; otherwise, preset the maximum usage time, obtain the hazard source usage time corresponding to the current accident type, and when the hazard source usage time exceeds the maximum usage time, generate early warning information based on the current accident type and the hazard source usage time; when the hazard source usage time does not exceed the maximum usage time, use the average data of historical data as real-time data.

[0019] A further optimization scheme is to determine the early warning information according to the hazard source monitoring time; including the method:

[0020] Obtain the first monitoring time of the hazard source corresponding to the current accident type;

[0021] Determine whether the first monitoring time is consistent with the current monitoring time. If not, generate an early warning message based on the current accident type and the first monitoring time.

[0022] A further optimization scheme is to obtain potential risks based on historical data; including the following methods:

[0023] Obtain historical accident levels for various types of historical accidents based on historical data;

[0024] A specified accident level is preset to determine whether the specified accident level exists in the historical accident level. If so, the accident type corresponding to the specified accident level is taken as the potential risk; otherwise, the potential risk is determined based on the number of historical accidents of each type.

[0025] A further optimization scheme is to determine the potential risk based on the number of accidents of each type of historical accidents, including the following methods:

[0026] Get the number of accidents corresponding to each type of historical accidents;

[0027] Preset the quantity threshold and speed threshold to determine whether the number of accidents of the current historical accident type exceeds the quantity threshold. If so, the current historical accident type is taken as a potential risk; otherwise, obtain the unit growth rate of the number of accidents of the current historical accident type, and when the unit growth rate exceeds the speed threshold, the current historical accident type is taken as a potential risk.

[0028] A further optimization scheme is to obtain potential risks based on historical data; and further includes a method:

[0029] Obtain the occurrence time of various types of historical accidents based on historical data;

[0030] Determine whether the occurrence time of the current historical accident type is the preset time. If so, take the current historical accident type as a potential risk.

[0031] This solution also provides a beam yard accident early warning system based on the Internet of Things, which is used to implement the above-mentioned beam yard accident early warning method based on the Internet of Things; the system includes:

[0032] The acquisition module is used to collect real-time and historical data of different accident types in the target beam yard;

[0033] A first warning module, configured to issue a first warning based on real-time data and historical data; the first warning includes issuing a data source warning based on real-time data and historical data;

[0034] The second warning module is used to make a second warning based on real-time data and historical data: obtaining the real-time risk level corresponding to each accident type according to the real-time data; presetting the risk level threshold to determine whether the real-time risk level exceeds the risk level threshold. If so, generating warning information based on the real-time data; otherwise, obtaining the potential risk according to the historical data, and generating warning information based on the potential risk.

[0035] This solution also provides a computer-readable medium on which a computer program is stored. The computer program is executed by a processor to implement the above-mentioned beam yard accident early warning method based on the Internet of Things.

[0036] This solution also provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the above-mentioned beam yard accident early warning method based on the Internet of Things.

[0037] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0038] The present invention provides an Internet of Things-based beam yard accident warning method, system, medium and electronic equipment; while judging whether there is an accident risk for different accident types in the beam yard based on factual data, it also analyzes and predicts the potential risk types with accident risks based on historical accident information. That is, while issuing a warning based on real-time data, it also analyzes and predicts the potential risk categories and issues a warning in combination with historical accident information. This not only helps to improve the comprehensiveness of the warning, but also helps to improve the accuracy of the warning, making it convenient for staff or related equipment to deal with the accident risks in the beam yard in advance, thereby helping to reduce the possibility of accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0039] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the examples. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be considered as limiting the scope. A person of ordinary skill in the art can also derive other relevant drawings based on these drawings without inventive effort. In the drawings:

[0040] Figure 1 This is a flow chart of the beam yard accident early warning method based on the Internet of Things;

[0041] Figure 2 This is a flowchart of the first early warning method;

[0042] Figure 3 A flowchart of a method for determining early warning information based on hazard source monitoring time;

[0043] Figure 4 A flowchart of the method for obtaining potential risks based on historical data;

[0044] Figure 5 A flowchart of the method for determining potential risks based on the number of historical accidents of each type;

[0045] Figure 6 This is a structural diagram of the beam yard accident warning system based on the Internet of Things. DETAILED DESCRIPTION

[0046] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with examples and drawings. The exemplary embodiments of the present invention and their descriptions are only used to explain the present invention and are not intended to limit the present invention.

[0047] The traditional beam yard monitoring system can alarm immediately after a fault occurs, but it has the disadvantage of not being able to reduce the possibility of accidents. In view of this, the present solution provides the following embodiments to solve the above technical problems.

[0048] Example 1

[0049] This embodiment provides a beam yard accident early warning method based on the Internet of Things, such as Figure 1 Shown, including:

[0050] Step 1: Collect real-time and historical data of different accident types in the target beam yard;

[0051] The target beam yard in this step is the beam yard that requires accident warning; the accident type is the type of accident that may occur in the target beam yard, including fire accidents, mechanical injury accidents, and quality accidents, etc.; the real-time data is the data obtained by real-time monitoring of different accident types, such as the real-time temperature of different equipment in the beam yard, the degree of damage and integrity of different equipment, and the quality of various beams produced in the beam yard;

[0052] Historical data includes real-time data within a time period such as the past year or the past two years; when the monitoring device starts collecting data at the next moment, the real-time data at the previous moment is changed into historical data and stored in a designated database; in this embodiment, a large number of IoT monitoring devices and various types of sensors are provided to monitor and collect factual data corresponding to different accident types.

[0053] Step 2: Perform a first warning based on real-time data and historical data; the first warning includes performing a data source warning based on real-time data and historical data; Figure 2 As shown, this step specifically includes the following method:

[0054] To determine whether real-time data and historical data exist for different accident types, a list of accident types can be pre-set, and different accident types can be detected one by one according to the list of accident types to determine whether corresponding real-time data and historical data exist. In this embodiment, the accident type list is a preset list, which stores all accident types that need to be monitored. The accident type list can be arranged in any order, and can also be arranged in descending order according to user needs or accident frequency.

[0055] Scenario 1: If no real-time or historical data exists for the current accident type, an early warning is generated based on the current accident type. If no real-time or historical data is detected, this indicates a problem with data collection and the risk of equipment failure, so an early warning is issued.

[0056] Scenario 2: If there is no real-time data for the current accident type, but there is historical data, the warning information is determined based on the abnormal conditions of the historical data.

[0057] The method for determining early warning information based on abnormal conditions of historical data specifically includes: judging whether the historical data is abnormal data, and if so, generating early warning information based on the current accident type and abnormal data; otherwise, presetting a maximum usage time, obtaining the hazard source usage time corresponding to the current accident type, and when the hazard source usage time exceeds the maximum usage time, generating early warning information based on the current accident type and the hazard source usage time; when the hazard source usage time does not exceed the maximum usage time, using the average data of historical data as real-time data.

[0058] In this embodiment, if only historical data is detected but real-time data is not detected, it indicates that there may be a problem with the data collection at that time. Further judgment is made as to whether there is abnormal data in the historical data. Abnormal data refers to data that is abnormal compared with the security data. It may be that the data is not within the range of security data, or that the relevant data is not detected.

[0059] If the usage time of the hazardous source exceeds the maximum usage time, it means that the current usage time of the hazardous source equipment (or component) has exceeded the rated usage time, and there is a greater risk of accident, so an early warning is required. If the current usage time of the hazardous source does not exceed the maximum usage time, it means that the current usage time of the hazardous source equipment (or component) does not exceed the rated usage time and is still within the safe usage range. Since the historical data is complete and there is no abnormal data, the average data can be calculated based on all historical data corresponding to the accident type, and the average data can be used as the real-time data collected this time. Of course, the real-time data can also be inferred based on the changes in historical data.

[0060] Scenario 3: If there is real-time data for the current accident type but no historical data, the warning information is determined based on the hazard source monitoring time.

[0061] Specific examples Figure 3 As shown, determining early warning information based on the hazard source monitoring time includes the following steps:

[0062] S21, obtaining the first monitoring time of the hazard source corresponding to the current accident type;

[0063] S22, determining whether the first monitoring time is consistent with the current monitoring time. If not, generating warning information based on the current accident type and the first monitoring time.

[0064] If there is no abnormal data in the historical data, it means that all historical data are complete and within the safe data range. In order to further determine whether there is an accident risk in the target beam yard, the current usage time of the hazard source corresponding to the accident type is obtained. In this embodiment, the hazard source is an item that requires data monitoring, such as lifting equipment (or related components of lifting equipment), fire extinguishing equipment, and various beams produced in the beam yard, etc., which may have accident risks. The current usage time is the length of time corresponding to the equipment (or component) from its official use to the present.

[0065] In this embodiment, if it is detected that there is real-time data but no historical data for the accident type, the first monitoring time of the hazard source corresponding to the accident type is further obtained to determine whether data collection has been performed on the accident type before this data collection. Therefore, it is necessary to obtain the first monitoring time of the hazard source corresponding to the accident type, wherein the first monitoring time is the time when data collection is first required or required for the accident type. The current monitoring time is the time when data collection is performed this time. In this embodiment, the corresponding first monitoring time is within the time range of the previous monitoring time and the next monitoring time. If the first monitoring time does not correspond to the current monitoring time, it means that the first monitoring time is not within the time range of the previous monitoring time and the next monitoring time, that is, it indicates that this data collection is not the first data collection for this accident type, that is, data collection has been performed on this accident type before, but it was also unsuccessful. Therefore, there must be problems with the data collection of this accident type, so an early warning is issued.

[0066] This implementation determines whether the equipment (or component) is expired based on the current usage time and maximum usage time of the hazard source corresponding to the accident type. If so, an early warning is issued. If not, the average data is calculated based on historical data and the average data is used as real-time data. The corresponding processing method is selected according to different situations, or an early warning is issued for the accident type, or the real-time data is predicted, which helps to improve the accuracy of the early warning.

[0067] Step three: perform a second warning based on real-time data and historical data: obtain the real-time risk level corresponding to each accident type based on real-time data; preset a risk level threshold to determine whether the real-time risk level exceeds the risk level threshold. If so, generate warning information based on real-time data; otherwise, obtain potential risks based on historical data, and generate warning information based on the potential risks.

[0068] This embodiment obtains the real-time risk level corresponding to different accident types based on factual data and determines whether the real-time risk level exceeds the risk level threshold. If it exceeds, it indicates that the real-time risk level corresponding to the accident type is too high and exceeds the safety range, which also indicates that there is a high accident risk for this accident type in the beam yard, and therefore an early warning is issued. If it does not exceed, it indicates that the real-time risk level corresponding to the accident type is not too high and has not yet exceeded the safety range. To further determine whether there is an accident risk for different accident types in the beam yard, potential risk types are obtained based on historical accident information, and early warning information is generated based on the potential risk types. While determining whether there is an accident risk for different accident types in the beam yard based on factual data, potential risk types that may have accident risks are also analyzed and predicted based on historical accident information. That is, while issuing early warnings based on real-time data, potential risk categories are analyzed, predicted, and issued in combination with historical accident information. This not only helps to improve the comprehensiveness of early warnings, but also helps to improve the accuracy of early warnings, making it easier for staff or related equipment to deal with accident risks in the beam yard in advance, thereby helping to reduce the possibility of accidents.

[0069] Specifically, the real-time risk level refers to the risk level corresponding to the real-time data. In this embodiment, the real-time risk level can be divided into levels one to five based on different accident types and the severity or potential danger level of the accident corresponding to the accident type, where level one corresponds to the lowest risk and level five corresponds to the highest risk. The risk level threshold is the criterion used to determine whether the risk of the actual data corresponding to the real-time risk level requires an early warning. In this embodiment, the risk level threshold can be set to level two or three, or can be set according to actual conditions and user needs.

[0070] In this embodiment, historical accidents can be classified into particularly serious accidents, serious accidents, major accidents, and general accidents based on the hazards and impact caused by the accidents. Among them, a particularly serious accident is one that meets at least one of the following conditions: direct economic losses of RMB 10 million or more, or leads to a major or more railway traffic accident, or has a significant impact on transportation production, safety, or railway construction safety, construction period, investment, etc.; a major accident is one that meets at least one of the following conditions: direct economic losses of RMB 5 million or more but less than RMB 10 million, or leads to a major railway traffic accident, or has a significant impact on transportation production, safety, or railway construction safety, construction period, investment, etc.; a major accident is one that meets at least one of the following conditions: direct economic losses of RMB 1 million or more but less than RMB 5 million, or directly leads to a general railway traffic accident, or has a significant impact on transportation production, safety, or railway construction safety, construction period, investment, etc.; and a general accident is one that meets at least one of the following conditions: direct economic losses of less than RMB 1 million, or directly leads to a general railway traffic accident, or has a general impact on transportation production, safety, or railway construction safety, construction period, investment, etc.

[0071] Generate early warning information based on real-time data, that is, information that provides early warning for the accident type corresponding to the real-time data in the beam yard, including the accident type, real-time risk level, accident location and other information related to the accident.

[0072] like Figure 4 As shown, in step three, the potential risk is obtained based on historical data; including the steps of:

[0073] S31, obtaining historical accident levels of various types of historical accidents based on historical data;

[0074] S32: A designated accident level is preset, and it is determined whether the designated accident level exists in the historical accident level. If so, the accident type corresponding to the designated accident level is determined as a potential risk. Otherwise, the potential risk is determined based on the number of historical accidents of each type. In this embodiment, the potential risk type refers to the accident type with a high potential risk, including high-risk accident types and accident types requiring key monitoring. The designated level can be either a particularly serious accident or a major accident.

[0075] In this embodiment, if there is a designated level in the historical accident level, it indicates that a particularly serious accident or a serious accident has occurred in this accident type, so this accident type needs to be paid special attention to and monitored. Therefore, when there is a designated level, this accident type is regarded as a potential risk type.

[0076] like Figure 5 As shown, in step S32, the potential risk is determined according to the number of accidents of each type of historical accidents, including the following method:

[0077] S321, obtaining the number of accidents corresponding to each type of historical accidents;

[0078] S322, preset the quantity threshold and speed threshold, determine whether the number of accidents of the current historical accident type exceeds the quantity threshold, if so, take the current historical accident type as a potential risk; otherwise, obtain the unit growth rate of the number of accidents of the current historical accident type, and when the unit growth rate exceeds the speed threshold, take the current historical accident type as a potential risk.

[0079] In this step, the preset number threshold is a pre-set judgment standard for determining whether the number of accidents corresponding to a certain accident type exceeds the safe number range within a certain time period (such as the past year). The preset number threshold can be 10 times. If the number of accidents exceeds the preset number threshold, it indicates that in the past year, a large number of accidents of this accident type has occurred, and the number has exceeded the allowed number. It is determined that this accident type has a large accident risk, and the accident type corresponding to the number of accidents is a potential risk type. If the number of accidents does not exceed the preset number threshold, it indicates that in the past year, no large number of accidents of this accident type has occurred, and the number has not exceeded the allowed number. In order to further determine whether this accident type has a large accident risk, the unit growth rate of the number of different accidents is further obtained, where the unit growth rate is the growth rate of the number of accidents of this accident type per unit time. If the unit growth rate exceeds the speed threshold, it indicates that the growth rate of this accident type per unit time is too fast, exceeding the maximum allowed unit growth rate. Therefore, this accident type has a large accident risk, and the accident type corresponding to the unit growth rate is regarded as a potential risk type.

[0080] In this embodiment, if the historical accident level does not match the specified level, it indicates that no particularly serious or major accidents have occurred for this accident type. Therefore, there is no need to focus on or monitor this accident type. To further determine whether this accident type has an accident risk, the number of accidents corresponding to different accident types is obtained, where the accident number is the total number of accidents of a certain accident type. Based on the number of accidents, the potential risk type is determined.

[0081] When there is a specified level in the historical accident level, it indicates that a particularly serious accident or a major accident has occurred in this accident type. In order to prevent this type of accident from happening again, this accident type needs to be monitored in key areas. Therefore, this type of accident type is directly regarded as a potential risk type. When there is no specified level in the historical accident level, it indicates that no particularly serious accident or a major accident has occurred in this accident type. The number of accidents corresponding to different accident types is further judged, and the potential risk type is obtained based on the number of accidents. Strengthening the key monitoring of accident types where particularly serious accidents or major accidents have occurred will help to provide early warning of the accident risks existing in this accident type, thereby reducing the possibility of this type of accident happening again.

[0082] This plan judges whether there is a large accident risk for different accident types based on the number of accidents and the unit growth rate corresponding to the accident types. If so, the accident type will be determined as a potential accident risk; accident types with a number of accidents exceeding the preset number threshold and a unit growth rate exceeding the speed threshold will be paid special attention to and monitored, which will help to deal with the accident risks of the accident type in advance, thereby helping to reduce the possibility of accidents.

[0083] In step three, the method of obtaining potential risks based on historical data also includes:

[0084] Obtain the occurrence time of various types of historical accidents based on historical data;

[0085] Determine whether the current historical accident type's occurrence time is a preset time. If so, use the current historical accident type as a potential risk. Accident-frequently occurring time nodes are time nodes at which accidents frequently occur. Different accident types have different frequent occurrence time nodes. For example, fires are more likely to occur in the summer. In this embodiment, the frequent occurrence time nodes corresponding to different accident types can be obtained from historical accident information. If the current time node is a frequent accident time node, it indicates that the accident type is likely to occur at the current time node. Therefore, the accident type corresponding to the frequent accident time node at the current time node is used as a potential risk type.

[0086] The Internet of Things-based beam yard accident warning method provided in this embodiment determines whether the current time node is a common time node corresponding to different accident types. If so, it indicates that there is a high possibility of an accident at the current time node. Therefore, the accident type corresponding to the current time node being a common accident time node is regarded as a potential risk type, so as to focus on and monitor the relevant data corresponding to the accident type. Once a problem is found, it is dealt with in a timely manner, which helps to reduce the possibility of accidents.

[0087] Example 2

[0088] This embodiment provides a beam yard accident early warning system based on the Internet of Things, which is used to implement the beam yard accident early warning method based on the Internet of Things described in Example 1; Figure 6 As shown, the system includes:

[0089] The acquisition module is used to collect real-time and historical data of different accident types in the target beam yard;

[0090] A first warning module, configured to issue a first warning based on real-time data and historical data; the first warning includes issuing a data source warning based on real-time data and historical data;

[0091] The second warning module is used to make a second warning based on real-time data and historical data: obtaining the real-time risk level corresponding to each accident type according to the real-time data; presetting the risk level threshold to determine whether the real-time risk level exceeds the risk level threshold. If so, generating warning information based on the real-time data; otherwise, obtaining the potential risk according to the historical data, and generating warning information based on the potential risk.

[0092] Example 3

[0093] This embodiment provides a computer-readable medium having a computer program stored thereon, wherein the computer program is executed by a processor to implement the beam yard accident early warning method based on the Internet of Things as described in Example 1; specifically, the following steps are performed:

[0094] Step 1: Collect real-time and historical data of different accident types in the target beam yard;

[0095] Step 2: Perform a first warning based on real-time data and historical data; the first warning includes performing a data source warning based on real-time data and historical data;

[0096] Step three: perform a second warning based on real-time data and historical data: obtain the real-time risk level corresponding to each accident type based on real-time data; preset a risk level threshold to determine whether the real-time risk level exceeds the risk level threshold. If so, generate warning information based on real-time data; otherwise, obtain potential risks based on historical data, and generate warning information based on the potential risks.

[0097] Example 4

[0098] This embodiment provides a computer device comprising a memory and a processor, wherein the memory stores a computer program, and wherein the processor implements the Internet of Things-based beam yard accident early warning method described in Example 1 when executing the computer program.

[0099] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. The beam yard accident early warning method based on the Internet of Things is characterized by: include: Collect real-time and historical data of different accident types in the target beam yard; First warning based on real-time and historical data; The first warning includes data source warning based on real-time data and historical data; Second warning based on real-time and historical data: obtain the real-time risk level corresponding to each accident type based on real-time data; Preset risk level thresholds to determine whether the real-time risk level exceeds the risk level threshold. If so, generate warning information based on real-time data; Otherwise, potential risks are obtained based on historical data, and early warning information is generated based on the potential risks.

2. The beam yard accident early warning method based on the Internet of Things according to claim 1 is characterized in that: The first warning based on real-time data and historical data includes the following methods: Determine whether real-time and historical data exist for different accident types: If there is no real-time data or historical data for the current accident type, then an early warning message is generated based on the current accident type; If there is no real-time data for the current accident type, but there is historical data, the warning information is determined based on the abnormal conditions of the historical data; If there is real-time data for the current accident type but no historical data, the warning information will be determined based on the hazard source monitoring time.

3. The beam yard accident early warning method based on the Internet of Things according to claim 2 is characterized in that: Determining early warning information based on abnormal conditions of historical data; Included methods: Determine whether the historical data is abnormal data. If so, generate warning information based on the current accident type and abnormal data; Otherwise, the maximum usage time is preset, and the usage time of the hazardous source corresponding to the current accident type is obtained. When the usage time of the hazardous source exceeds the maximum usage time, an early warning message is generated based on the current accident type and the usage time of the hazardous source; When the usage time of the hazardous source does not exceed the maximum usage time, the average data of historical data is used as the real-time data.

4. The beam yard accident early warning method based on the Internet of Things according to claim 2 is characterized in that: Determining the early warning information according to the hazard source monitoring time; Included methods: Obtain the first monitoring time of the hazard source corresponding to the current accident type; Determine whether the first monitoring time is consistent with the current monitoring time. If not, generate an early warning message based on the current accident type and the first monitoring time.

5. The beam yard accident early warning method based on the Internet of Things according to claim 1 is characterized in that: The method of obtaining potential risks based on historical data includes: Obtain historical accident levels for various types of historical accidents based on historical data; A specified accident level is preset to determine whether the specified accident level exists in the historical accident level. If so, the accident type corresponding to the specified accident level is taken as the potential risk; otherwise, the potential risk is determined based on the number of historical accidents of each type.

6. The beam yard accident early warning method based on the Internet of Things according to claim 5 is characterized in that: The method of determining potential risks based on the number of historical accidents of each type includes: Get the number of accidents corresponding to each type of historical accidents; Preset quantity thresholds and speed thresholds to determine whether the number of accidents of the current historical accident type exceeds the quantity threshold. If so, the current historical accident type is considered a potential risk; Otherwise, obtain the unit growth rate of the number of accidents of the current historical accident type, and when the unit growth rate exceeds the speed threshold, take the current historical accident type as a potential risk.

7. The beam yard accident early warning method based on the Internet of Things according to claim 1 is characterized in that: The method of obtaining potential risks based on historical data also includes: Obtain the occurrence time of various types of historical accidents based on historical data; Determine whether the occurrence time of the current historical accident type is the preset time. If so, take the current historical accident type as a potential risk.

8. The beam yard accident warning system based on the Internet of Things is characterized by: Used to implement the beam yard accident early warning method based on the Internet of Things as described in any one of claims 1 to 7; The system comprises: The acquisition module is used to collect real-time and historical data of different accident types in the target beam yard; A first warning module, configured to issue a first warning based on real-time data and historical data; the first warning includes issuing a data source warning based on real-time data and historical data; The second warning module is used to make a second warning based on real-time data and historical data: obtaining the real-time risk level corresponding to each accident type according to the real-time data; presetting the risk level threshold to determine whether the real-time risk level exceeds the risk level threshold. If so, generating warning information based on the real-time data; otherwise, obtaining the potential risk according to the historical data, and generating warning information based on the potential risk.

9. A computer-readable medium having a computer program stored thereon, characterized in that: The computer program is executed by a processor to implement the beam yard accident early warning method based on the Internet of Things as described in any one of claims 1 to 7.

10. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that When the processor executes the computer program, the beam yard accident warning method based on the Internet of Things as described in any one of claims 1 to 7 is implemented.

Images