Risk assessment method and device, electronic equipment and storage medium

Abstract

The application discloses a risk assessment method and device, electronic equipment and storage medium, and relates to the technical field of safe operation and risk assessment. The method comprises the following steps: acquiring a plurality of position images, a sound array and a temperature array of a target production device in a target factory area, and analyzing the plurality of position images, the sound array and the temperature array to obtain a device risk assessment result; acquiring video data in the target factory area, and determining the operation behavior of a staff in the target factory area and material storage information; determining a staff risk assessment result based on the operation behavior of the staff, and determining a material placement risk assessment result based on the material storage information; and determining a risk assessment result of the target factory area based on the device risk assessment result, the staff risk assessment result and the material placement risk assessment result. The scheme of the application can quickly and accurately perform risk assessment on a chemical plant, and identify potential risks to provide help for the safety management of the chemical plant.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of safe operation and risk assessment, and particularly relates to a risk assessment method and device, electronic equipment and a storage medium. BACKGROUND

[0002] A chemical plant, also known as a chemical factory or a chemical plant, is an industrial facility that specializes in the production, processing and handling of chemicals. These plants convert raw materials into various useful chemicals through a series of complex chemical reactions and physical operations, including basic chemicals (such as sulfuric acid, ammonia), fine chemicals (such as pharmaceuticals, fragrances) and specialty chemicals (such as paints, adhesives).

[0003] Risk assessment of chemical plants is a systematic process aimed at identifying, analyzing and controlling potential risks to ensure the safety of personnel, environmental protection and stable operation of production facilities. Risk assessment not only helps prevent accidents, but also improves compliance and optimizes resource allocation for more efficient safety management.

[0004] How to quickly and accurately assess the risks of chemical plants, identify potential risks, and provide help for the safety management of chemical plants is a key issue in the industry. SUMMARY

[0005] The present application provides a risk assessment method, device, electronic equipment and storage medium to quickly and accurately assess the risks of chemical plants, identify potential risks, and provide help for the safety management of chemical plants.

[0006] According to an aspect of the present application, a risk assessment method is provided, the method comprising:

[0007] Respectively, image collection, sound monitoring and temperature monitoring of at least two target positions of the target production equipment in the target plant area are performed to obtain a plurality of position images, sound arrays and temperature arrays;

[0008] Respectively, the sound array and the temperature array are analyzed for abnormalities to obtain a sound anomaly coefficient array and a temperature anomaly coefficient array, and a first anomaly coefficient array is obtained based on the sound anomaly coefficient array and the temperature anomaly coefficient array;

[0009] Based on each of the position images, the target production equipment is identified for damage to obtain a device damage coefficient array, a risk coefficient is determined based on the device damage coefficient array and the first anomaly coefficient array, and a device risk assessment result of the target production equipment is determined based on the risk coefficient;

[0010] The uncontrollable coefficient array of the target factory area is determined based on the risk assessment results of the devices, and the risk assessment result of the target factory area is determined according to the uncontrollable coefficient array of the target factory area.

[0011] According to another aspect of the present application, a risk assessment device is provided, which comprises:

[0012] The data acquisition module is configured to acquire images, monitor sounds, and monitor temperatures at at least two target positions of the target production device in the target factory area, to obtain a plurality of position images, a sound array, and a temperature array.

[0013] The first abnormal coefficient array determination module is configured to perform abnormality analysis on the sound array and the temperature array, to obtain a sound abnormal coefficient array and a temperature abnormal coefficient array, and to obtain a first abnormal coefficient array based on the sound abnormal coefficient array and the temperature abnormal coefficient array.

[0014] The device risk assessment result determination module is configured to identify damages of the target production device based on the position images, to obtain a device damage coefficient array, to determine a risk coefficient based on the device damage coefficient array and the first abnormal coefficient array, and to determine a device risk assessment result of the target production device based on the risk coefficient.

[0015] The factory area risk assessment result determination module is configured to determine an uncontrollable coefficient array of the target factory area based on the risk assessment results of the devices, and to determine a risk assessment result of the target factory area according to the uncontrollable coefficient array of the target factory area.

[0016] According to another aspect of the present application, an electronic device is provided, which comprises:

[0017] at least one processor; and

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

[0019] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor to enable the at least one processor to execute the risk assessment method according to any one of the embodiments of the present application.

[0020] According to another aspect of the present application, a computer readable storage medium is provided, which stores computer instructions for enabling a processor to execute the risk assessment method according to any one of the embodiments of the present application.

[0021] According to another aspect of the present application, there is provided a computer program product comprising a computer program which, when executed by a processor, implements the risk assessment method according to any of the embodiments of the present application.

[0022] The technical scheme of the embodiment of the present application obtains a plurality of position images, a sound array and a temperature array by respectively performing image collection, sound monitoring and temperature monitoring on the target production equipment in the target factory area at at least two target positions; respectively performs abnormality analysis on the sound array and the temperature array to obtain a sound abnormality coefficient array and a temperature abnormality coefficient array, and obtains a first abnormality coefficient array based on the sound abnormality coefficient array and the temperature abnormality coefficient array; performs damage identification on the target production equipment based on each position image to obtain a device damage coefficient array, determines a risk coefficient based on the device damage coefficient array and the first abnormality coefficient array, and determines a device risk assessment result of the target production equipment based on the risk coefficient; determines an uncontrollable coefficient array of the target factory area based on each device risk assessment result, and determines a risk assessment result of the target factory area according to the uncontrollable coefficient array of the target factory area, so that the risk assessment of the chemical plant can be quickly and accurately performed, the potential risk can be identified, and the safety management of the chemical plant can be facilitated.

[0023] It should be understood that the content described in this part is not intended to identify key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become apparent from the following description. BRIEF DESCRIPTION OF DRAWINGS

[0024] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can also be obtained by those skilled in the art without creative labor.

[0025] Figure 1 is a flowchart of a risk assessment method according to an embodiment of the present application;

[0026] Figure 2 is a flowchart of a risk assessment method according to an embodiment of the present application;

[0027] Figure 3 is a flowchart of a risk assessment method according to an embodiment of the present application;

[0028] Figure 4 is a flowchart of a risk assessment method according to an embodiment of the present application;

[0029] Figure 5 is a structural schematic diagram of a risk assessment device according to an embodiment of the present application;

[0030] Figure 6 is a structural schematic diagram of an electronic device implementing a risk assessment method according to an embodiment of the present application. DETAILED DESCRIPTION

[0031] In order to make the personnel in the technical field better understand the present application scheme, the technical scheme in the embodiment of the present application will be described clearly and completely in the following with reference to the drawings in the embodiment of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor should belong to the scope of protection of the present application.

[0032] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not necessarily limit to those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0033] In the description of the present application, the word "for example" is used to mean "serving as an example, instance, or illustration". Any embodiment described as "for example" in the present application is not necessarily to be construed as more preferred or advantageous over other embodiments. The following description is presented to enable any person skilled in the art to make and use the present application. In the following description, for the purpose of explanation, details are set forth. It should be appreciated that one of ordinary skill in the art can realize the application without using these specific details. In other instances, well-known structures and processes are not described in detail in order to avoid obscuring the description of the present application. Therefore, the present application is not intended to be limited to the embodiments shown, but is to be accorded the widest scope consistent with the principles and features disclosed.

[0034] Embodiment one

[0035] Figure 1is a flow chart of a risk assessment method according to an embodiment of the present application, the embodiment can be applicable to the case of safety risk assessment on production equipment in the chemical industry, and the method can be executed by a risk assessment device which can be realized in the form of hardware and / or software and can be configured in a computer, a server or an electronic device such as a tablet computer. Figure 1 As shown in the figure, the method comprises the following steps.

[0036] Step 110: image collection, sound monitoring and temperature monitoring are respectively performed on at least two target positions of the target production equipment in the target factory area to obtain a plurality of position images, sound arrays and temperature arrays.

[0037] In the embodiment, the target factory area can be a production factory area, a storage factory area or a use factory area of a chemical product, and is not limited in the embodiment.

[0038] In the embodiment, the target production equipment can be a production equipment, a storage equipment or a transportation equipment of a dangerous chemical, and is not limited in the embodiment; in the embodiment, the number of the target production equipment can be multiple, for example, all the storage equipment in the target factory area, and is not limited in the embodiment.

[0039] It can be understood that in the risk assessment of the production and storage equipment of a dangerous chemical, the valve and the weld are the key parts of the equipment, and the aging and damage of these areas can cause the equipment to leak and further cause a safety accident; the valve and the weld are the areas most prone to aging and damage on the storage tank, the valve is in a state of pressure change and on-off operation for a long time, and the weld is the welded part of the storage tank and is prone to cracks and corrosion due to stress concentration; at the same time, the damage and leakage of these areas usually show temperature change and sound anomaly, so the monitoring of the valve and the weld positions is very critical.

[0040] Accordingly, the target position can be a valve position or a weld position in the target production equipment, or can be other key parts, and is not limited in the embodiment.

[0041] In this embodiment, in order to ensure comprehensive monitoring of the status of these target positions (valves and welds), multiple sensors and monitoring devices need to be installed near the valves and welds to collect relevant data in real time; for example, image data, sound data and temperature data can be collected, for example, using a high-definition camera or infrared imager to regularly take images of the valve and weld area, especially at the joint of the valve and weld, where small cracks or corrosion points may occur, which are usually difficult to detect by the naked eye, but can be captured by infrared imaging; acoustic sensors are installed at the valve and weld to collect sound data in real time, and when the valve and weld are damaged, there may be a small amount of leakage sound or metal friction sound, which can reflect the working state of the equipment, and these sound data will help analyze the abnormal situation of the equipment and identify whether there is a leak or other potential failure; temperature sensors are installed around the valve and weld to monitor temperature changes at multiple locations in real time, and when the equipment is damaged or aged, it usually accompanies abnormal rise or fall of local temperature, especially at the joint of the valve and weld, temperature anomaly may be a precursor to leakage or corrosion.

[0042] Optionally, in this embodiment, at least two target positions of the target production equipment in the target factory area are respectively subjected to image collection, sound monitoring and temperature monitoring to obtain multiple position images, sound arrays and temperature arrays, which can include: obtaining target positions of the target production equipment, and respectively collecting position images, sound data and temperature data of each target position; wherein the target positions include: valves and welds; obtaining the sound array based on the position information of each target position and each sound data; obtaining the temperature array based on the position information of each target position and each temperature data.

[0043] In one optional implementation of this embodiment, the target positions of key components such as valves or welds can be determined based on design drawings of the target production equipment, and further, image data of each target position can be collected by an image sensor; sound data of each target position can be collected by a microphone array; temperature data of each target position can be collected by a temperature sensor.

[0044] Further, the sound array can be obtained based on the position information of each target position, for example, the position information of each target position and each sound data; the temperature array can be obtained based on the position information of each target position and each temperature data.

[0045] In one specific example of this embodiment, the sound data collected by each sound sensor can form a sound array according to the position coordinates of each target position; the temperature data of multiple positions can form a temperature array according to the position coordinates of each target position.

[0046] The scheme of the embodiment can provide comprehensive data support for real-time state monitoring of the target production equipment by collecting image, sound and temperature data of multiple key positions (valves and welds) of the target production equipment, and can reflect dynamic changes of the equipment in real time through integration and analysis of the multi-dimensional data, thereby significantly improving risk assessment capability of the storage tank equipment.

[0047] Step 120, respectively, abnormality analysis is performed on the sound array and the temperature array to obtain a sound abnormality coefficient array and a temperature abnormality coefficient array, and a first abnormality coefficient array is obtained based on the sound abnormality coefficient array and the temperature abnormality coefficient array.

[0048] Optionally, in the embodiment, after the sound array and the temperature array of each target position are determined, further, abnormality analysis can be performed based on the sound array and the temperature array respectively, so as to obtain a sound abnormality coefficient array and a temperature abnormality coefficient array; further, a first abnormality coefficient array can be determined based on the sound abnormality coefficient array and the temperature abnormality coefficient array.

[0049] In one optional implementation manner of the embodiment, the sound array of the target position can be compared with the standard sound of the target position, so as to obtain abnormality analysis results of the sound array and a sound abnormality coefficient array.

[0050] In another optional implementation manner of the embodiment, the temperature array of the target position can be compared with the standard temperature of the target position, so as to obtain abnormality analysis results of the temperature array and a temperature abnormality coefficient array.

[0051] Further, the sound abnormality coefficient array and the temperature abnormality coefficient array can be merged, so as to obtain a first abnormality coefficient array.

[0052] Step 130, damage identification is performed on the target production equipment based on the image of each position to obtain an equipment damage coefficient array, a risk coefficient is determined based on the equipment damage coefficient array and the first abnormality coefficient array, and a device risk assessment result of the target production equipment is determined based on the risk coefficient.

[0053] Optionally, in the embodiment, after the multiple position images of the target position are collected, further damage identification can be performed on each position image, for example, damage path identification, damage degree identification or damage category identification can be performed on each position image, and further, an equipment damage coefficient array can be obtained based on the identification result.

[0054] Further, a damage risk coefficient of the target position can be determined based on the equipment damage coefficient array and the first abnormality coefficient array.

[0055] In an optional implementation of the embodiment, the obtained position images and the coordinate information of the target positions corresponding to the position images can be input into the first large model that is pre-tuned to output a device damage coefficient array.

[0056] Further, the determined device damage coefficient array and the first abnormal coefficient array can be input into a second large model that is pre-tuned to output a risk coefficient. The risk coefficient can be a probability value, for example, a probability of occurrence of a risk. In the embodiment, the risk coefficient can be a probability value of occurrence of a dangerous event at each target position or a probability value of occurrence of a dangerous event at the target production device as a whole, which is not limited in the embodiment.

[0057] Optionally, in the embodiment, after the risk coefficient is determined, a risk level corresponding to the risk coefficient can be further determined, and the risk level can be further determined as a device risk assessment result.

[0058] The risk level can be low, medium, or high, or can be a first level to a tenth level, and the higher the level, the more dangerous.

[0059] In an optional implementation of the embodiment, if the risk level of the device risk assessment result is greater than a preset level, that is, the probability of occurrence of a dangerous event at the target production device is high, an alarm can be issued to prompt relevant personnel to perform maintenance or evacuate in time to prevent the occurrence of a safety accident.

[0060] In an optional implementation of the embodiment, if the risk level of the device risk assessment result is greater than a preset level, that is, the probability of occurrence of a dangerous event at the target production device is high, an alarm can be issued to prompt relevant personnel to perform maintenance or evacuate in time to prevent the occurrence of a safety accident.

[0061] Optionally, in the embodiment, after the device risk assessment result of each production device is obtained, the uncontrolled coefficient array of the target factory area can be further determined based on the device risk assessment result, and the risk assessment result of the target factory area can be further determined based on the uncontrolled coefficient array of the target factory area.

[0062] Optionally, in the embodiment, based on the risk assessment result of each device, the uncontrollable coefficient array of the target factory area is determined, and the risk assessment result of the target factory area is determined according to the uncontrollable coefficient array of the target factory area, which can include: obtaining the device risk assessment result of all target devices in the target factory area, determining the uncontrollable coefficient array based on the uncontrollable coefficient in each risk assessment result and the position information of each target device; obtaining the target position information of the emergency resource stored in the target factory area; determining the uncontrollable coefficient of the target factory area according to the uncontrollable coefficient array and the target position information, and determining the uncontrollable coefficient as the risk assessment result of the target factory area.

[0063] In the embodiment, after the risk assessment of the production device is performed, a plurality of same devices are generally configured in the factory area. Based on the steps in the foregoing content, the risk assessment of a plurality of same devices is performed, the uncontrollable coefficients are obtained respectively, the uncontrollable coefficient array of a plurality of devices is constructed, and the risk assessment of the factory area is further performed to obtain the risk assessment result of the factory area.

[0064] In the embodiment, a plurality of same devices as the target device, such as a plurality of storage tanks, are generally arranged in the factory area to support production. The steps in the foregoing content are used to perform the monitoring risk assessment on a plurality of same devices to obtain the uncontrollable coefficients of a plurality of same devices of the target device in the factory area.

[0065] Further, the device positions of a plurality of same devices are obtained, for example, the latitude and longitude coordinates of each same device in the factory area are obtained as the device position, and then the uncontrollable coefficients of a plurality of same devices are labeled according to the positions to construct the uncontrollable coefficient array.

[0066] Further, the position of the emergency resource in the factory area is obtained, for example, the position of the fire extinguishing and first aid device is obtained, and if a plurality of emergency resources are arranged in the factory area, the position coordinates of a plurality of emergency resources are obtained.

[0067] Then, according to the uncontrollable coefficient array and the emergency resource position, the distance between the device position of each same device and the nearest emergency resource position is calculated to obtain a plurality of emergency distances. The emergency distance can be calculated according to the device position coordinates of the same device and the coordinates of the emergency resource position.

[0068] Further, according to the size of a plurality of emergency distances, a weight is configured, for example, the ratio of each emergency distance to a plurality of emergency distances is calculated to obtain a plurality of weights, and then the plurality of weights are used to perform weighted calculation on a plurality of uncontrollable coefficients in the uncontrollable coefficient array to obtain the uncontrollable coefficients of a plurality of same devices in the factory area based on the weighted calculation of the emergency distance as the factory uncontrollable coefficient as the risk assessment result of the factory area. Wherein, the larger the emergency distance is, the greater the danger of the uncontrollable risk of the corresponding device is, and therefore, the larger the proportion of the factory uncontrollable coefficient is.

[0069] Understandably, the higher the factory area out-of-control coefficient, the greater the probability of uncontrollable risks such as leakage incidents occurring in the factory area as a whole. Based on this, it provides equipment maintenance personnel with decision-making references for factory equipment maintenance, such as carrying out equipment refurbishment and maintenance for the entire factory area.

[0070] The technical solution of this embodiment involves acquiring images, monitoring sound, and monitoring temperature at at least two target locations of the target production equipment within the target plant area, thereby obtaining multiple location images, sound arrays, and temperature arrays. Anomaly analysis is then performed on the sound arrays and temperature arrays to obtain sound anomaly coefficient arrays and temperature anomaly coefficient arrays, and a first anomaly coefficient array is derived based on these arrays. Damage identification is performed on the target production equipment based on each location image, resulting in an equipment damage coefficient array. A risk coefficient is determined based on the equipment damage coefficient array and the first anomaly coefficient array, and an equipment risk assessment result for the target production equipment is determined based on the risk coefficients. Finally, an uncontrollable coefficient array for the target plant area is determined based on the risk assessment results of each equipment, and the overall risk assessment result for the target plant area is determined based on this uncontrollable coefficient array. This approach allows for rapid and accurate risk assessment of chemical plants, identification of potential risks, and assistance in the safety management of chemical plants.

[0071] Example 2

[0072] Figure 2 This is a flowchart of a risk assessment method according to Embodiment 2 of the present invention. This embodiment is a further refinement of the above technical solution, and the technical solution in this embodiment can be combined with various optional solutions in one or more of the above embodiments. Figure 2 As shown, the method includes:

[0073] Step 210: Perform image acquisition, sound monitoring, and temperature monitoring at at least two target locations for the target production equipment within the target factory area, and obtain multiple location images, sound arrays, and temperature arrays.

[0074] Step 220: Obtain standard sound data and standard temperature data; determine the first magnitude of deviation of each sound data in the sound array from the standard sound data, and determine a sound anomaly coefficient array based on each of the first magnitudes; and determine the second magnitude of deviation of each temperature data in the temperature array from the standard temperature data, and determine a temperature anomaly coefficient array based on each of the second magnitudes.

[0075] In the embodiment, the standard sound data and the standard temperature data are reference values for determining whether the target production equipment is abnormal, and can be obtained by long-time monitoring and data collection.

[0076] In an optional implementation of the embodiment, the standard sound data can be obtained as follows: a plurality of acoustic sensors are installed at a plurality of target positions (such as valve and welding seam) of the target production equipment to collect sound data when the equipment is running normally; then, statistical analysis is performed on the sound data of the plurality of target positions to obtain the standard sound data of each position. The standard sound can be established by calculating the sound pressure level (dB) and frequency, and the average value of a plurality of data points is usually taken, and the acoustic characteristics of the equipment under different loads and temperatures are considered.

[0077] In another optional implementation of the embodiment, the standard temperature data can be obtained as follows: when the target production equipment is running normally, temperature data of each target position of the equipment is collected by a temperature sensor, especially in the damaged areas such as valve and welding seam, to collect standard temperature data; then, the temperature data of different positions are statistically analyzed to obtain the standard temperature of each position. The standard temperature is usually obtained by averaging the temperature of the equipment running stably for a period of time to ensure that the typical temperature of the equipment under normal working condition can be reflected.

[0078] Further, a first amplitude of each sound data in the sound array deviating from the standard sound data can be determined, and a sound anomaly coefficient array is determined based on the first amplitudes. In a specific implementation, a sound difference value of each sound data in the sound array and the standard sound data can be determined respectively, and a first ratio of each sound difference value to the standard sound can be calculated respectively, each ratio is stored in a set order to obtain the sound anomaly coefficient array.

[0079] Further, a second amplitude of each temperature data in the temperature array deviating from the standard temperature data can be determined, and a temperature anomaly coefficient array is determined based on the second amplitudes. In a specific implementation, a temperature difference value of each temperature data in the temperature array and the standard temperature data can be determined respectively, and a second ratio of each temperature difference value to the standard temperature can be calculated respectively, each ratio is stored in a set order to obtain the temperature anomaly coefficient array.

[0080] Optionally, a sound difference value (such as a sound pressure level difference value) of each sound in the sound array and the standard sound is calculated to obtain a plurality of sound difference values; then, an absolute value of each sound difference value and the standard sound are calculated respectively, and the ratio is set as a sound anomaly coefficient, as follows: ; wherein, is the sound anomaly coefficient, for the sound in the sound array, for the standard sound.

[0081] In the present embodiment, the sound difference (e.g. sound pressure level difference) between each sound in the sound array and the standard sound data can be calculated to obtain a plurality of sound differences; then, the absolute value of each sound difference is calculated and divided by the standard sound to obtain a sound anomaly coefficient, which reflects the deviation between the collected sound and the standard sound, and a sound anomaly coefficient array is generated, which can be shown in Table 1 as follows:

[0082] Table 1: Sound anomaly coefficient table

[0083]

[0084] On the other hand, the temperature difference between each temperature in the temperature array and the standard temperature data is calculated to obtain a plurality of temperature differences, and the absolute value of each temperature difference is calculated and divided by the standard temperature to obtain a temperature anomaly coefficient, as follows: ; wherein, is the temperature anomaly coefficient, is the temperature in the temperature array, is the standard temperature.

[0085] It can be understood that the temperature anomaly coefficient reflects the deviation between the collected temperature and the standard temperature, and the larger the temperature difference, the larger the temperature anomaly coefficient, indicating that there is a more obvious temperature anomaly at this position, suggesting that there may be equipment damage or failure. A temperature anomaly coefficient array is constructed, which can be shown in Table 2 as follows:

[0086] Table 2: Temperature anomaly coefficient table

[0087]

[0088] By calculating the ratio of the sound and temperature difference to the standard value, the sound and temperature anomaly coefficient at each position can be obtained, which can effectively reflect the abnormal state of the equipment at each position. The larger the value of the anomaly coefficient, the greater the deviation, and the higher the risk of equipment failure or leakage. By continuously monitoring these sound / temperature anomaly coefficients, potential equipment problems can be discovered in a timely manner.

[0089] Step 230, merging the sound anomaly coefficient array and the temperature anomaly coefficient array to obtain the first anomaly coefficient array.

[0090] Optionally, in the present embodiment, after the sound anomaly coefficient array and the temperature anomaly coefficient array are determined based on the above steps, the sound anomaly coefficient array and the temperature anomaly coefficient array can be further combined to obtain the first anomaly coefficient array involved in the present embodiment.

[0091] In an optional implementation of the present embodiment, according to the sound anomaly coefficient array and the temperature anomaly coefficient array, the mean value of the sound anomaly coefficient and the temperature anomaly coefficient of each position can be calculated, and the mean value calculation result is taken as the basic anomaly coefficient of the position to construct the first anomaly coefficient array, wherein the basic anomaly coefficient table is shown in Table 3 as follows:

[0092] Table 3: Basic anomaly coefficient table

[0093]

[0094] It should be noted that in the present embodiment, the first anomaly coefficient array is obtained by comprehensively considering the mean value calculation of the sound anomaly coefficient and the temperature anomaly coefficient. This array can provide a comprehensive anomaly evaluation result for further risk analysis. The position with a larger basic anomaly coefficient in the equipment may have a more significant fault or potential problem.

[0095] Step 240, performing production equipment damage identification on each position image to obtain an equipment damage coefficient array.

[0096] Step 250, performing damage identification on the target production equipment based on each position image to obtain an equipment damage coefficient array, determining a risk coefficient based on the equipment damage coefficient array and the first anomaly coefficient array.

[0097] Step 260, determining the equipment risk evaluation result of the target production equipment based on the risk coefficient.

[0098] Step 270, determining an uncontrollable coefficient array of the target plant area based on each equipment risk evaluation result, and determining the risk evaluation result of the target plant area according to the uncontrollable coefficient array of the target plant area.

[0099] The scheme of the embodiment is to obtain standard sound data and standard temperature data, determine a first amplitude at which each sound data in the sound array deviates from the standard sound data, determine a sound anomaly coefficient array based on each first amplitude, determine a second amplitude at which each temperature data in the temperature array deviates from the standard temperature data, determine a temperature anomaly coefficient array based on each second amplitude, and combine the sound anomaly coefficient array and the temperature anomaly coefficient array to obtain the first anomaly coefficient array. The sound array and the temperature array can be accurately analyzed for anomaly, and the analysis result can be integrated to obtain the first anomaly coefficient array, thereby providing a basis for risk assessment of subsequent production equipment.

[0100] Embodiment three

[0101] Figure 3 is a flowchart of a risk assessment method according to the embodiment two of the present application. The embodiment is a further refinement of the above technical solution, and the technical solution in the embodiment can be combined with each optional solution in one or more of the above embodiments. As shown in the figure, the method comprises: Figure 3

[0102] Step 310: image collection, sound monitoring, and temperature monitoring are respectively performed on at least two target positions of a target production equipment in a target factory area to obtain a plurality of position images, a sound array, and a temperature array.

[0103] Step 320: anomaly analysis is respectively performed on the sound array and the temperature array to obtain a sound anomaly coefficient array and a temperature anomaly coefficient array, and a first anomaly coefficient array is obtained based on the sound anomaly coefficient array and the temperature anomaly coefficient array.

[0104] Step 330: each position image is input into a damage path recognition model for recognition to obtain a device damage coefficient array.

[0105] Optionally, in the embodiment, after the position images of each target position are obtained, the obtained position images can be further input into the damage path recognition model for recognition to obtain the device damage coefficient array.

[0106] Optionally, in the embodiment, the damage path recognition model can be obtained by the following steps: a sample position image set of different positions of different production equipment is obtained, and a damage coefficient of each sample position image is labeled to obtain a sample damage coefficient set; wherein the damage coefficient is a ratio of a damage size to a maximum damage size of a corresponding position; a damage recognition path corresponding to each different position is constructed; and the sample position image set, the sample damage coefficient set, and each damage recognition path are iteratively trained to obtain the damage path recognition model.​

[0107] In a specific implementation, according to the aging damage monitoring data of the same type of equipment of the target production equipment, a sample position image set of different positions of different production equipment can be collected, that is, for multiple key positions (such as valves, welds, etc.) of the same type of equipment, image samples of these positions are obtained through image acquisition technology. These images will show whether the equipment has damage (such as cracks, corrosion, dents, etc.), and provide data support for subsequent damage analysis. Further, the damage coefficient in each sample position image is labeled. The damage coefficient is the ratio of the damage size (the actual size of the damage area obtained through image analysis) and the maximum damage size of the corresponding position (the maximum damage size allowed at this position, which is usually determined according to factors such as equipment design standards, material strength, etc.). A sample damage coefficient set is obtained. For example, the sample damage coefficient can be as shown in Table 4:

[0108] Table 4: Sample Damage Coefficient Table

[0109]

[0110] It can be understood that the damage coefficient reflects the damage degree of the equipment at the target position, can quantify the relative size of the damage, and is used for risk assessment and equipment health management. By collecting images of the target position of the equipment and performing damage analysis, the damage coefficient of each position can be calculated, providing a basis for subsequent safety assessment.

[0111] Further, the damage identification path of each device position (such as a valve, a weld, etc.) can be constructed based on a convolutional neural network, which can automatically identify damage patterns in the image, such as cracks, corrosion, and indentation, through a feature extraction layer. Each path corresponds to a device position, and the input image data will be specially processed and identified according to the features of the position. The damage identification path includes an input layer, a convolutional layer (used for convolutional feature extraction, such as cracks, corrosion, etc., each convolutional kernel extracts features from the input image through convolutional operation), a pooling layer (used for down-sampling, reducing the size of the feature map, while preserving important spatial feature information, and reducing the amount of calculation), a fully connected layer (integrating the features extracted by convolution and pooling, outputting a high-dimensional feature vector), and an output layer. The input data of the input layer is the device position image, and the output data is the damage coefficient. Further, the multiple sample position image sets and multiple sample damage coefficient sets are used to supervise the training of the multiple damage identification paths, for example, the first sample position image set and the first sample damage coefficient set corresponding to the first position are used to supervise the training of the damage identification path. First, the input image is passed into the network for forward propagation, and then the features are extracted through the convolutional layer and the pooling layer, and then the features are integrated through the fully connected layer, and finally the predicted damage coefficient is calculated through the output layer. Further, the error between the predicted damage coefficient and the true label (true damage coefficient) is calculated through the mean square error loss function. Further, the gradient of the loss function with respect to the network parameters (convolutional kernel, weight, etc.) is calculated through the backpropagation algorithm, and the network parameters are updated to gradually reduce the prediction error. In each round of training, the weights and biases of the convolutional neural network are updated through the gradient descent or optimization algorithm to minimize the loss function, so that the predicted value of the damage coefficient is closer to the true value. The above forward propagation, loss calculation, backpropagation, and parameter updating processes are repeated until the training accuracy of the network reaches the predetermined standard, the loss function converges, and the first damage identification path is obtained.

[0112] In this embodiment, the loss function of each damage identification path is as follows:

[0113] ;

[0114] wherein, is the loss, N is the data quantity in the sample position image set and the sample damage coefficient set, is the damage coefficient identified by the damage identification path after the i-th group of sample position images is input, is the i-th group of sample damage coefficients.

[0115] Further, the plurality of position images are respectively input into corresponding plurality of damage identification paths for identification, and a plurality of damage coefficients are output to construct a device damage coefficient array. According to the damage identification path based on the convolutional neural network, the damage feature recognition can improve the intelligence and automation of the damage coefficient analysis, thereby effectively improving the efficiency and accuracy of the damage calculation and analysis, and providing accurate data support for the device risk assessment.

[0116] In step 340, a risk coefficient is determined based on the device damage coefficient array and the first abnormal coefficient array.

[0117] Optionally, in the embodiment, the determination of the risk coefficient based on the device damage coefficient array and the first abnormal coefficient array can include: in the case where the first dimension of the device damage coefficient array is the same as the second dimension of the first abnormal coefficient array, determining the product of each first coefficient of the device damage coefficient array and each second coefficient of the first abnormal coefficient array to obtain a risk coefficient array; determining the array mean of the risk coefficient array, and determining the array mean as the risk coefficient; or in the case where the first dimension of the device damage coefficient array is not the same as the second dimension of the first abnormal coefficient array, performing a completion operation on the device damage coefficient array or the first abnormal coefficient array based on a preset rule to make the first dimension of the device damage coefficient array the same as the second dimension of the first abnormal coefficient array.

[0118] In another optional implementation manner of the embodiment, the determination of the risk coefficient based on the device damage coefficient array and the first abnormal coefficient array can further include: acquiring historical basic abnormal coefficient data of each device under different damage states from historical operation and monitoring data of the same type of device according to the risk monitoring data of the same type of device; then, for each device damage coefficient, acquiring all corresponding basic abnormal coefficients in the historical monitoring data and calculating their average value to obtain a historical average basic abnormal coefficient; further acquiring the historical average basic abnormal coefficient of each device damage coefficient in the device damage coefficient array to construct a historical basic abnormal coefficient array.

[0119] Further, the similarity between the basic abnormal coefficient and the historical basic abnormal coefficient under the same position can be analyzed according to the basic abnormal coefficient array and the historical basic abnormal coefficient array. The purpose of the similarity calculation is to measure the similarity between the current basic abnormal coefficient and the historical basic abnormal coefficient. For example, the absolute value of the difference between the basic abnormal coefficient and the historical basic abnormal coefficient is calculated, and the ratio of the absolute value to the historical basic abnormal coefficient is calculated. Then, 1 is subtracted from the ratio, and the difference is set as the similarity. The formula is as follows:

[0120] wherein,​ is a risk verification coefficient, is a basic abnormality coefficient, is a historical basic abnormality coefficient.

[0121] For example, assuming that the basic abnormality coefficient is 0.06 and the historical basic abnormality coefficient is 0.08, the similarity of the two is 1 minus 0.02 / 0.08, which equals 0.75, that is, the similarity is 75%, wherein the smaller the difference between the basic abnormality coefficient and the historical basic abnormality coefficient, the smaller the ratio, and the greater the similarity. The similarity is taken as the risk verification coefficient, and a risk verification coefficient array is constructed.

[0122] Further, according to the basic abnormality coefficient array and the risk verification coefficient array, the product of each basic abnormality coefficient and risk verification coefficient at the same position is calculated, the product of the two is taken as the risk coefficient of the position, a plurality of risk coefficients at a plurality of positions are obtained, and a risk coefficient array is constructed. Finally, the plurality of risk coefficients at the plurality of positions are mean calculated, and the mean calculation result is taken as the risk coefficient, which represents the overall risk level of the device.

[0123] Step 350, determining the device risk assessment result of the target production device based on the risk coefficient.

[0124] Optionally, in the embodiment, determining the device risk assessment result of the target production device based on the risk coefficient can include: obtaining historical operation and maintenance data of the target production device, determining maintenance information of each target position in historical time based on the historical operation and maintenance data, and obtaining a historical operation and maintenance data array; determining a historical evaluation device damage coefficient of each historical operation and maintenance data pair in the historical operation and maintenance data array, and obtaining a historical device damage coefficient array; determining the similarity of each historical device damage coefficient and the device damage coefficient according to the historical device damage coefficient array and the device damage coefficient array, and obtaining a damage verification coefficient array; determining the mean of the damage verification coefficient array, and determining the mean as a controllable coefficient; determining a controllable risk coefficient based on the product of the controllable coefficient and the risk coefficient, or determining an uncontrollable coefficient based on the product of the uncontrollable coefficient and the risk coefficient; wherein the sum of the controllable coefficient and the uncontrollable coefficient is 1; determining the controllable risk coefficient or the uncontrollable coefficient as the device risk assessment result.

[0125] The scheme of the embodiment is to obtain the number of operation and maintenance of the plurality of positions in a historical time (such as the last three months) according to the historical operation and maintenance data of the target device, the number of operation and maintenance reflecting the use and maintenance frequency of different positions, and being capable of providing relevant information of device aging and damage, wherein the more the number of operation and maintenance is, the more serious the aging of the position is, and the greater the amplitude of device damage is, and a historical operation and maintenance data array is constructed. On the other hand, the historical average device damage coefficient of each historical operation and maintenance data in the historical operation and maintenance data array is obtained according to the risk monitoring data of the same type of device, the historical average device damage coefficient being calculated based on the operation history data of the same type of device and reflecting the degree of device damage of each position, and a historical device damage coefficient array is obtained.

[0126] Further, the similarity of each historical device damage coefficient and the device damage coefficient in the same position can be calculated according to the historical device damage coefficient array and the device damage coefficient array. First, the ratio of the absolute value of the difference between the historical device damage coefficient and the device damage coefficient to the historical device damage coefficient is calculated, and the difference between 1 and the ratio is taken as the damage coefficient similarity, a plurality of damage coefficient similarities of a plurality of positions are obtained, the damage coefficient similarity is taken as a damage verification coefficient, and a damage verification coefficient array is constructed. Then, the plurality of damage verification coefficients in the damage verification coefficient array are subjected to mean value calculation, and the mean value calculation result is taken as a controllable coefficient; then, the difference between 1 and the controllable coefficient is taken as an uncontrollable coefficient. Finally, the controllable risk coefficient is obtained by multiplying the controllable coefficient by the risk coefficient, the uncontrollable coefficient is obtained by multiplying the uncontrollable coefficient by the risk coefficient, and the controllable risk coefficient and the uncontrollable coefficient are taken as the device risk assessment result.

[0127] It can be understood that the greater the uncontrollable coefficient is, the greater the abnormal amplitude caused by other damage in addition to the damage caused by normal operation and maintenance of the target device is, and the greater the controllable risk coefficient is, the greater the abnormal amplitude of the damage caused by normal operation and maintenance of the target device is. It can be used for reference by device maintenance personnel to perform device maintenance or scrap processing, and timely transfer of chemicals to avoid risk events. For example, the uncontrollable coefficient and the controllable risk coefficient of the same type of device that has occurred leakage and other accidents can be distinguished to perform further maintenance processing.

[0128] The scheme of the embodiment of the application can effectively distinguish controllable and uncontrollable risks by analyzing the similarity of the historical device damage coefficient and the current device damage coefficient, and dynamically assesses according to the actual status and aging condition of the device. This method significantly improves the accuracy of risk assessment, can help the maintenance team to preferentially process high-risk areas or preferentially process areas with a larger uncontrollable coefficient, and improves the scientificity and efficiency of device management.

[0129] Step 360, determining the uncontrollable coefficient array of the target factory based on the risk assessment result of each device, and determining the risk assessment result of the target factory according to the uncontrollable coefficient array of the target factory.

[0130] The scheme of the embodiment of the present application obtains a plurality of position images, a sound array and a temperature array by image acquisition, sound monitoring and temperature monitoring of a plurality of positions of a target device; then, according to a standard sound and a standard temperature, abnormal analysis is performed on the sound array and the temperature array to obtain a sound abnormal coefficient array and a temperature abnormal coefficient array, and a basic abnormal coefficient array is calculated and obtained; further, device damage identification is performed on the plurality of position images to obtain a device damage coefficient array, damage verification is performed on the basic abnormal coefficient array to obtain a risk coefficient array, and a risk coefficient is calculated and obtained; then, a historical operation and maintenance data array of the plurality of positions is collected, controllable damage verification is performed on the device damage coefficient array to calculate and obtain a controllable coefficient and an uncontrollable coefficient; finally, the controllable coefficient and the uncontrollable coefficient are multiplied by the risk coefficient to obtain a controllable risk coefficient and an uncontrollable risk coefficient as the device risk assessment result; that is, by combining multi-dimensional data and intelligent algorithms, dynamic assessment of device safety risk can be realized, and by generating controllable device risk assessment results and uncontrollable device risk assessment results, changes in the device can be more accurately reflected, the scientificity, timeliness and accuracy of the device risk assessment result can be significantly improved, thereby effectively reducing misjudgment and omissions, and improving the safety and reliability of device storage.

[0131] Embodiment Four

[0132] Figure 4 is a flowchart of a risk assessment method according to the embodiment four of the present application, and the technical scheme in the embodiment is further refined to the above technical scheme, and can be combined with each optional scheme in one or more of the above embodiments. As shown in the figure, the method comprises: Figure 4

[0133] Step 410, image acquisition, sound monitoring and temperature monitoring are performed on at least two target positions of a target production device in a target factory to obtain a plurality of position images, a sound array and a temperature array.

[0134] Step 420, abnormal analysis is performed on the sound array and the temperature array to obtain a sound abnormal coefficient array and a temperature abnormal coefficient array, and a first abnormal coefficient array is obtained based on the sound abnormal coefficient array and the temperature abnormal coefficient array.

[0135] ​Step 430, damage identification is performed on the target production equipment based on each of the position images, an equipment damage coefficient array is obtained, a risk coefficient is determined based on the equipment damage coefficient array and the first abnormality coefficient array, and an equipment risk evaluation result of the target production equipment is determined based on the risk coefficient.

[0136] Step 440, video data in the target factory area is acquired, the video data is analyzed to obtain operation behaviors of workers in the target factory area and material storage information in the target factory area, a worker risk evaluation result is determined based on the operation behaviors of the workers in the target factory area, and a material placement risk evaluation result is determined based on the material storage information in the target factory area, and a risk evaluation result of the target factory area is determined based on the equipment risk evaluation result, the worker risk evaluation result, and the material placement risk evaluation result.

[0137] In this embodiment, the operation behaviors of the workers can include work behaviors of the workers, and can also include safety behaviors such as whether the workers wear safety helmets, and are not limited in this embodiment.

[0138] Optionally, in this embodiment, after the equipment risk evaluation result of the target production equipment is acquired, video data in the target factory area can be further acquired through each camera device deployed in the target factory area, and the acquired video data can be further analyzed, for example, the acquired video data can be input into a pre-tuned video data analysis large model, so as to obtain operation behaviors of workers in the target factory area and material storage information in the target factory area.

[0139] Further, a worker risk evaluation result can be determined based on the operation behaviors of the workers in the target factory area, and a material placement risk evaluation result can be determined based on the material information in the target factory area; for example, in this embodiment, the worker risk evaluation result and the material placement risk evaluation result can be respectively determined based on a pre-tuned operation behavior risk evaluation large model and a material placement risk evaluation large model.

[0140] Further, a risk evaluation result of the target factory area can be determined based on the equipment risk evaluation result, the worker risk evaluation result, and the material placement risk evaluation result; for example, different weights can be set for the equipment risk evaluation result, the worker risk evaluation result, and the material placement risk evaluation result based on actual situations, and further, products of each weight value and each risk evaluation result can be summed to obtain a final risk evaluation result.

[0141] The scheme of the embodiment can acquire video data in the target factory area, analyze the video data, obtain operation behaviors of workers in the target factory area and material storage information in the target factory area, determine worker risk assessment results based on the operation behaviors of the workers in the target factory area and determine material placement risk assessment results based on the material storage information in the target factory area, and determine the risk assessment results of the target factory area based on the device risk assessment results, the worker risk assessment results, and the material placement risk assessment results. The risk assessment results of the target factory area can be determined based on different dimensions, which provides a basis for accurately determining the risk assessment results of the target factory area.

[0142] Embodiment five

[0143] Figure 5 is a structural schematic diagram of a risk assessment device provided according to Embodiment five of the present application. As shown in the figure, the device comprises a data acquisition module 510, a first abnormal coefficient array determination module 520, a device risk assessment result determination module 530, and a factory area risk assessment result determination module 540. Figure 5

[0144] The data acquisition module 510 is configured to perform image acquisition, sound monitoring, and temperature monitoring on at least two target positions of a target production device in a target factory area, to obtain a plurality of position images, a sound array, and a temperature array.

[0145] The first abnormal coefficient array determination module 520 is configured to perform abnormal analysis on the sound array and the temperature array to obtain a sound abnormal coefficient array and a temperature abnormal coefficient array, and to obtain a first abnormal coefficient array based on the sound abnormal coefficient array and the temperature abnormal coefficient array.

[0146] The device risk assessment result determination module 530 is configured to perform damage identification on the target production device based on each position image to obtain a device damage coefficient array, to determine a risk coefficient based on the device damage coefficient array and the first abnormal coefficient array, and to determine a device risk assessment result of the target production device based on the risk coefficient.

[0147] The factory area risk assessment result determination module 540 is configured to determine an uncontrollable coefficient array of the target factory area based on each device risk assessment result, and to determine a risk assessment result of the target factory area according to the uncontrollable coefficient array of the target factory area.

[0148] ​The scheme of the embodiment is that the data acquisition module respectively performs image acquisition, sound monitoring and temperature monitoring on target production equipment in a target factory area at at least two target positions to obtain a plurality of position images, a sound array and a temperature array; the first abnormal coefficient array determination module respectively performs abnormal analysis on the sound array and the temperature array to obtain a sound abnormal coefficient array and a temperature abnormal coefficient array, and obtains a first abnormal coefficient array based on the sound abnormal coefficient array and the temperature abnormal coefficient array; the equipment risk assessment result determination module identifies damage of the target production equipment based on the position images to obtain an equipment damage coefficient array, determines a risk coefficient based on the equipment damage coefficient array and the first abnormal coefficient array, and determines an equipment risk assessment result of the target production equipment based on the risk coefficient; the factory area risk assessment result determination module determines an uncontrollable coefficient array of the target factory area based on the equipment risk assessment results, and determines a risk assessment result of the target factory area according to the uncontrollable coefficient array of the target factory area, so that the chemical plant can be quickly and accurately risk assessed, potential risks can be identified, and help can be provided for safety management of the chemical plant.

[0149] In an optional implementation manner of the embodiment, the data acquisition module 510 is specifically configured to acquire target positions of the target production equipment, and respectively acquire position images, sound data and temperature data of each target position; wherein the target positions include a valve and a weld;

[0150] The sound array is obtained based on position information of each target position and each sound data.

[0151] The temperature array is obtained based on position information of each target position and each temperature data.

[0152] In an optional implementation manner of the embodiment, the first abnormal coefficient array determination module 520 is specifically configured to acquire standard sound data and standard temperature data.

[0153] A first amplitude of each sound data in the sound array deviating from the standard sound data is determined, and a sound abnormal coefficient array is determined based on each first amplitude; and

[0154] A second amplitude of each temperature data in the temperature array deviating from the standard temperature data is determined, and a temperature abnormal coefficient array is determined based on each second amplitude.

[0155] The sound abnormal coefficient array and the temperature abnormal coefficient array are combined to obtain the first abnormal coefficient array.

[0156] In an optional implementation of the embodiment, the first abnormal coefficient array determination module 520 is further configured to determine a sound difference value of each sound data in the sound array and the standard sound data respectively, calculate a first ratio of each sound difference value and the standard sound respectively, store each ratio in a set order, and obtain the sound abnormal coefficient array; and

[0157] determine a temperature difference value of each temperature data in the temperature array and the standard temperature data respectively, calculate a second ratio of each temperature difference value and the standard temperature respectively, store each ratio in a set order, and obtain the temperature abnormal coefficient array.

[0158] In an optional implementation of the embodiment, the device risk assessment result determination module 530 is configured to input each position image into a damage path recognition model to obtain the device damage coefficient array.

[0159] The damage path recognition model is obtained through the following steps:

[0160] A sample position image set of different positions of different production devices is obtained, and a damage coefficient of each sample position image is labeled to obtain a sample damage coefficient set; wherein the damage coefficient is a ratio of a damage size and a maximum damage size corresponding to the position.

[0161] A damage recognition path corresponding to each position is constructed.

[0162] The sample position image set, the sample damage coefficient set, and each damage recognition path are iteratively trained to obtain the damage path recognition model.

[0163] In a case where the first dimension of the device damage coefficient array is the same as the second dimension of the first abnormal coefficient array, a product of each first coefficient of the device damage coefficient array and each second coefficient of the first abnormal coefficient array is determined to obtain a risk coefficient array.

[0164] An array mean of the risk coefficient array is determined, and the array mean is determined as the risk coefficient.

[0165] Alternatively,

[0166] In a case where the first dimension of the device damage coefficient array is not the same as the second dimension of the first abnormal coefficient array, a preset rule is used to perform a completion operation on the device damage coefficient array or the first abnormal coefficient array, so that the first dimension of the device damage coefficient array is the same as the second dimension of the first abnormal coefficient array.

[0167] obtain historical maintenance data of the target production equipment, determine maintenance information of each target position in a historical time based on the historical maintenance data, and obtain a historical maintenance data array;

[0168] determine a historical equipment damage coefficient of each historical maintenance data in the historical maintenance data array, and obtain a historical equipment damage coefficient array;

[0169] determine a similarity between each historical equipment damage coefficient and the equipment damage coefficient based on the historical equipment damage coefficient array and the equipment damage coefficient array, and obtain a damage verification coefficient array;

[0170] determine a mean value of the damage verification coefficient array, and determine the mean value as a controllable coefficient;

[0171] determine a controllable risk coefficient based on a product of the controllable coefficient and the risk coefficient, or determine an uncontrollable coefficient based on a product of the uncontrollable coefficient and the risk coefficient; wherein a sum of the controllable coefficient and the uncontrollable coefficient is 1;

[0172] determine the controllable risk coefficient or the uncontrollable coefficient as the equipment risk assessment result.

[0173] In an optional implementation of the embodiment, the plant risk assessment result determination module 540 is specifically configured to obtain equipment risk assessment results of all target equipment in the target plant, and determine an uncontrollable coefficient array based on uncontrollable coefficients in each risk assessment result and position information of each target equipment.

[0174] obtain target position information of a target position where an emergency resource is stored in the target plant;

[0175] determine an uncontrollable coefficient of the target plant based on the uncontrollable coefficient array and the target position information, and determine the uncontrollable coefficient of the target plant as a risk assessment result of the target plant.

[0176] In an optional implementation of the embodiment, the risk assessment device further includes a comprehensive risk assessment module configured to obtain video data in the target plant, analyze the video data, obtain operation behaviors of workers in the target plant, and obtain material storage information in the target plant.

[0177] determine a worker risk assessment result based on the operation behaviors of the workers in the target plant, and determine a material placement risk assessment result based on the material storage information in the target plant.

[0178] determine a risk assessment result of the target plant based on the equipment risk assessment result, the worker risk assessment result, and the material placement risk assessment result.

[0179] The risk assessment device provided by the embodiments of the present application can execute the risk assessment method provided by any of the embodiments of the present application, and has the corresponding function modules and beneficial effects of the execution method.

[0180] In the technical solutions of the embodiments of the present application, the collection, storage, use, processing, transmission, provision and disclosure of the data (such as image data, sound data and temperature data) of the production equipment all comply with the relevant legal regulations and do not violate public order and good customs.

[0181] Embodiment six

[0182] Figure 6 A structural schematic diagram of an electronic device 10 that can be used to implement embodiments of the present application is shown. The electronic device is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices (e.g., headsets, glasses, watches, etc.), and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present application described and / or claimed in this document.

[0183] As shown in Figure 6 The electronic device 10 includes at least one processor 11, and a memory, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., which is communicatively connected to the at least one processor 11, wherein the memory stores a computer program that can be executed by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0184] A plurality of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, a loudspeaker, etc.; a storage unit 18, such as a magnetic disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network, such as the Internet, and / or various telecommunication networks.

[0185] The processor 11 can be various general and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs various methods and processes described above, such as a risk assessment method, which includes: performing image collection, sound monitoring, and temperature monitoring on at least two target positions of a target production device in a target factory respectively, to obtain a plurality of position images, a sound array, and a temperature array; performing anomaly analysis on the sound array and the temperature array respectively to obtain a sound anomaly coefficient array and a temperature anomaly coefficient array, and obtaining a first anomaly coefficient array based on the sound anomaly coefficient array and the temperature anomaly coefficient array; performing damage identification on the target production device based on each of the position images to obtain a device damage coefficient array, determining a risk coefficient based on the device damage coefficient array and the first anomaly coefficient array, and determining a device risk assessment result of the target production device based on the risk coefficient; determining an uncontrollable coefficient array of the target factory based on each device risk assessment result, and determining a risk assessment result of the target factory according to the uncontrollable coefficient array of the target factory.

[0186] In some embodiments, the risk assessment method can be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the risk assessment method described above can be performed. Alternatively, in other embodiments, the processor 11 can be configured to perform the risk assessment method by any other appropriate means, such as by means of firmware.

[0187] The various embodiments of the systems and techniques described above can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a load programmable logic device (CPLD), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0188] Computer programs used to implement the processes of the application can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer program

[0189] In the context of the present application, a computer-readable storage medium can be a tangible medium that can contain or store computer programs for use by or in connection with an instruction execution system, apparatus, or device. Computer-readable storage media can include, but are not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium will include one or more lines of a program of instructions in a transitory signal, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0190] To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the electronic device. Other kinds of devices can be used to provide for interaction with a user as well; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form, including acoustic, speech, or tactile input.

[0191] The systems and techniques described here can be implemented in a computing system that includes a back end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front end component (e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back end, middleware, or front end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0192] The computing system can include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. A server can be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system, to solve the defects of large management difficulty and weak business scalability in traditional physical host and VPS service.

[0193] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the scope of the present disclosure. For example, the steps recited in the present disclosure can be executed in parallel, executed in sequence, or executed in a different order, as long as the desired results of the present disclosure are achieved, and the present disclosure is not limited herein.

[0194] The above detailed description does not limit the scope of the present disclosure. It is understood that various modifications, combinations, sub-combinations, and alternatives can be made to the detailed disclosure without departing from the spirit and principles of the present disclosure. Any modifications, equivalent substitutions, improvements, and the like that are made within the spirit and principles of the present disclosure are included in the scope of the present disclosure.

[0195] The embodiment of the present application further provides a computer program product comprising a computer program which, when executed by a processor, implements the database detection method provided by any of the embodiments of the present application.

[0196] The computer program product can be written in one or more programming languages or combinations of languages including object-oriented languages, such as Java, Smalltalk, C++, and conventional procedural languages, such as the "C" programming language or similar programming languages. The program code can execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or the connection can be made to an external computer (for example, through the Internet using an Internet Service Provider).

[0197] It should be noted that in the embodiments of the present application, some software, components, models and other prior art solutions can be mentioned, which should be considered as exemplary, and the purpose is only to illustrate the feasibility of the implementation of the technical solutions of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0198] Note that the above are only the preferred embodiments of the present application and the technical principles applied. Those skilled in the art will understand that the present application is not limited to the specific embodiments herein, and those skilled in the art can make various obvious changes, readjustments and substitutions without departing from the scope of the present application. Therefore, although the present application has been described in more detail through the above embodiments, the present application is not limited to the above embodiments, and can include more other equivalent embodiments without departing from the concept of the present application, and the scope of the present application is determined by the scope of the appended claims.

Claims

1. A risk assessment method, characterized in that, include: Image acquisition, sound monitoring, and temperature monitoring are performed at at least two target locations for the target production equipment within the target factory area, resulting in multiple location images, sound arrays, and temperature arrays. Anomaly analysis is performed on the sound array and the temperature array respectively to obtain a sound anomaly coefficient array and a temperature anomaly coefficient array, and a first anomaly coefficient array is obtained based on the sound anomaly coefficient array and the temperature anomaly array; Damage identification is performed on the target production equipment based on the location images to obtain an equipment damage coefficient array. A risk coefficient is determined based on the equipment damage coefficient array and the first abnormal coefficient array. The equipment risk assessment result of the target production equipment is determined based on the risk coefficient. Based on the risk assessment results of each piece of equipment, the array of uncontrollable coefficients of the target plant area is determined, and the risk assessment result of the target plant area is determined according to the array of uncontrollable coefficients of the target plant area. The step of determining the equipment risk assessment result of the target production equipment based on the risk coefficient includes: obtaining historical operation and maintenance data of the target production equipment, determining the maintenance information of each target location within a historical time period based on the historical operation and maintenance data, and obtaining a historical operation and maintenance data array; Determine the historical average equipment damage coefficient corresponding to each historical operation and maintenance data in the historical operation and maintenance data array to obtain the historical equipment damage coefficient array. Based on the historical equipment damage coefficient array and the equipment damage coefficient array, the similarity between each historical equipment damage coefficient and the equipment damage coefficient is determined to obtain the damage verification coefficient array. Determine the mean of the damage verification coefficient array, and use the mean as a controllable coefficient; The controllable risk coefficient is determined based on the product of the controllable coefficient and the risk coefficient, or the uncontrollable risk coefficient is determined based on the product of the uncontrollable coefficient and the risk coefficient; wherein the sum of the controllable coefficient and the uncontrollable coefficient is 1. The controllable risk coefficient or the uncontrollable risk coefficient is determined as the equipment risk assessment result; The process of determining the uncontrollable coefficient array of the target plant area based on the risk assessment results of each piece of equipment, and determining the risk assessment result of the target plant area based on the uncontrollable coefficient array of the target plant area, includes: Obtain the equipment risk assessment results of all target equipment in the target factory area, and determine the uncontrollable coefficient array based on the uncontrollable coefficients in each risk assessment result and the location information of each target equipment. Obtain the target location information of the emergency resources stored in the target factory area; Based on the uncontrollable coefficient array and the target location information, the uncontrollability coefficient of the target plant area is determined, and the uncontrollability coefficient is determined as the risk assessment result of the target plant area.

2. The risk assessment method according to claim 1, characterized in that, The process involves acquiring images, monitoring sound, and monitoring temperature at at least two target locations within the target factory area for the target production equipment, resulting in multiple location images, sound arrays, and temperature arrays, including: The target location of the target production equipment is obtained, and location images, sound data, and temperature data of each target location are collected respectively; wherein, the target location includes: valves and welds; The sound array is obtained based on the location information of each target location and the sound data of each target location; The temperature array is obtained based on the location information of each target location and the temperature data of each target location.

3. The risk assessment method according to claim 1, characterized in that, The step of performing anomaly analysis on the sound array and the temperature array respectively to obtain a sound anomaly coefficient array and a temperature anomaly coefficient array, and obtaining a first anomaly coefficient array based on the sound anomaly coefficient array and the temperature anomaly array, includes: Acquire standard sound data and standard temperature data; Determine a first magnitude by which each sound data in the sound array deviates from the standard sound data, and determine a sound anomaly coefficient array based on each of the first magnitudes; and... Determine the second magnitude by which each temperature data in the temperature array deviates from the standard temperature data, and determine a temperature anomaly coefficient array based on each of the second magnitudes; The sound anomaly coefficient array and the temperature anomaly coefficient array are merged to obtain the first anomaly coefficient array.

4. The risk assessment method according to claim 3, characterized in that, The step involves determining a first magnitude by which each sound data in the sound array deviates from the standard sound data, and then determining a sound anomaly coefficient array based on each of the first magnitudes. And, determining a second magnitude of deviation of each temperature data point in the temperature array from the standard temperature data, and determining a temperature anomaly coefficient array based on each of the second magnitudes, including: The sound difference between each sound data in the sound array and the standard sound data is determined, and the first ratio of each sound difference to the standard sound is calculated. The ratios are stored in a set order to obtain the sound anomaly coefficient array. as well as, The temperature difference between each temperature data in the temperature array and the standard temperature data is determined, and the second ratio of each temperature difference to the standard temperature is calculated. The ratios are stored in a set order to obtain the temperature anomaly coefficient array.

5. The risk assessment method according to claim 1, characterized in that, The step of identifying damage to the target production equipment based on the location images to obtain an equipment damage coefficient array, determining a risk coefficient based on the equipment damage coefficient array and the first anomaly coefficient array, and determining the equipment risk assessment result of the target production equipment based on the risk coefficient includes: The images of each location are input into the damage path recognition model for recognition, thereby obtaining the equipment damage coefficient array; The damage path identification model is obtained through the following steps: A set of sample location images of different locations of different production equipment is obtained, and the damage coefficient of each sample location image is labeled to obtain a set of sample damage coefficients; where the damage coefficient is the ratio of the damage size to the maximum damage size at the corresponding location. Construct damage identification paths corresponding to different locations; The damage path recognition model is obtained by iteratively training based on the set of sample location images, the set of sample damage coefficients, and each of the damage recognition paths. When the first dimension of the equipment damage coefficient array is the same as the second dimension of the first anomaly coefficient array, the product of each first coefficient of the equipment damage coefficient array and each second coefficient of the first anomaly coefficient array is determined to obtain the risk coefficient array. or, If the first dimension of the equipment damage coefficient array is different from the second dimension of the first abnormal coefficient array, a completion operation is performed on the equipment damage coefficient array or the first abnormal coefficient array based on a preset rule so that the first dimension of the equipment damage coefficient array is the same as the second dimension of the first abnormal coefficient array. Determine the array mean of the risk coefficient array, and use the array mean as the risk coefficient.

6. The risk assessment method according to claim 1, characterized in that, The method further includes: Acquire video data within the target factory area, analyze the video data to obtain the operational behavior of the staff within the target factory area, and the material storage information within the target factory area; The risk assessment results for staff are determined based on their operational behavior within the target factory area, and the risk assessment results for material placement are determined based on the material storage information within the target factory area. The risk assessment results for the target plant area are determined based on the equipment risk assessment results, the staff risk assessment results, and the material placement risk assessment results.

7. A risk assessment device, characterized in that, include: The data acquisition module is used to acquire images, monitor sound, and monitor temperature at at least two target locations of the target production equipment in the target factory area, and obtain multiple location images, sound arrays, and temperature arrays. The first anomaly coefficient array determination module is used to perform anomaly analysis on the sound array and the temperature array respectively to obtain the sound anomaly coefficient array and the temperature anomaly coefficient array, and to obtain the first anomaly coefficient array based on the sound anomaly coefficient array and the temperature anomaly array. The equipment risk assessment result determination module is used to identify damage to the target production equipment based on the images of each location, obtain an equipment damage coefficient array, determine a risk coefficient based on the equipment damage coefficient array and the first abnormal coefficient array, and determine the equipment risk assessment result of the target production equipment based on the risk coefficient. The plant area risk assessment result determination module is used to determine the uncontrollable coefficient array of the target plant area based on the risk assessment results of each piece of equipment, and to determine the risk assessment result of the target plant area based on the uncontrollable coefficient array of the target plant area; The equipment risk assessment result determination module is specifically used to obtain the historical operation and maintenance data of the target production equipment, determine the maintenance information of each target location within a historical time period based on the historical operation and maintenance data, and obtain a historical operation and maintenance data array; Determine the historical average equipment damage coefficient corresponding to each historical operation and maintenance data in the historical operation and maintenance data array to obtain the historical equipment damage coefficient array. Based on the historical equipment damage coefficient array and the equipment damage coefficient array, the similarity between each historical equipment damage coefficient and the equipment damage coefficient is determined to obtain the damage verification coefficient array. Determine the mean of the damage verification coefficient array, and use the mean as a controllable coefficient; The controllable risk coefficient is determined based on the product of the controllable coefficient and the risk coefficient, or the uncontrollable risk coefficient is determined based on the product of the uncontrollable coefficient and the risk coefficient; wherein the sum of the controllable coefficient and the uncontrollable coefficient is 1. The controllable risk coefficient or the uncontrollable risk coefficient is determined as the equipment risk assessment result; The factory risk assessment result determination module is specifically used to obtain the equipment risk assessment results of all target equipment in the target factory area, and determine the uncontrollable coefficient array based on the uncontrollable coefficients in each risk assessment result and the location information of each target equipment. Obtain the target location information of the emergency resources stored in the target factory area; Based on the uncontrollable coefficient array and the target location information, the uncontrollability coefficient of the target plant area is determined, and the uncontrollability coefficient is determined as the risk assessment result of the target plant area.

8. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the risk assessment method according to any one of claims 1-6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute the risk assessment method according to any one of claims 1-6.

Images