A mountainous highway electromechanical equipment facility operation monitoring method and system

Abstract

The application discloses a mountainous highway electromechanical equipment and facility operation monitoring method and system, relates to the technical field of equipment monitoring, and comprises the following steps: according to the geographical environment information of a target mountainous area, constructing an information collection position of the target area, and collecting state data information of each equipment in real time. The application can effectively judge whether the monitored equipment in the area needs to be regulated in advance by evaluating the abnormal risk of each equipment and combining the historical operation data of the equipment, and output corresponding pre-regulation instructions to prevent potential faults and ensure the stable operation of the mountainous highway electromechanical equipment and facility. That is, the application not only improves the accuracy of highway equipment monitoring, but also greatly enhances the reliability and safety of equipment operation. Meanwhile, the monitoring strategy and pre-regulation instructions can be continuously adjusted according to the actual operation condition to adapt to the complex and changeable operation environment of the mountainous highway.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of equipment monitoring, in particular to a mountainous highway electromechanical equipment facility operation monitoring method and system. BACKGROUND

[0002] The mountainous highway has complex geographical environment, large undulating topography, variable and extreme climate (rain, snow, fog, freeze, strong wind, and large temperature difference), weak signal coverage, poor electromechanical facility operation environment, and complex fault inducement. The traditional monitoring method for the electromechanical equipment facilities in this area mainly relies on the over-limit alarm of fixed threshold, and can only respond after the fault occurs, which cannot realize fault prediction, resulting in untimely maintenance and affecting traffic safety. The operation and maintenance decision (such as maintenance opportunity and resource scheduling) is seriously dependent on manual experience, and manual scheduling is required for regular inspection, and false positives are prone to occur, resulting in low monitoring efficiency and high cost of the equipment facilities, and the state of the mountainous equipment facilities cannot be well monitored. SUMMARY

[0003] The present application relates to the technical field of equipment monitoring, in particular to a mountainous highway electromechanical equipment facility operation monitoring method and system.

[0004] In order to achieve the above purpose, the present application adopts the following technical scheme:

[0005] The present application provides a mountainous highway electromechanical equipment facility operation monitoring method in the first aspect, comprising:

[0006] According to the geographical environment information of the target mountainous area, the information collection position of the target area is constructed, and the state data information of each equipment is collected in real time;

[0007] According to the information collection position of the target area, the state data information of each equipment is processed to obtain the effective data information of each equipment;

[0008] The effective data information of each equipment is extracted to obtain the multi-dimensional state feature information of each equipment;

[0009] Real-time traffic data of the target mountainous area is collected in real time, and combined with the multi-dimensional state feature information of each equipment, the abnormal risk assessment information of each equipment is generated;

[0010] According to the abnormal risk assessment information of each equipment, and combined with the past historical data of each key equipment, the risk equipment pre-control instruction is output.

[0011] In a feasible scheme, it further comprises:

[0012] According to geographical environment information of the target mountainous area and in combination with an information collection position of the target area, at least one device execution chain is acquired;

[0013] The device execution chain comprises an execution unit composed of multiple devices.

[0014] The overall state of each device execution chain is evaluated to obtain overall state evaluation information of each device execution chain.

[0015] The overall state evaluation information of the device execution chain is compared with a preset chain state evaluation threshold to determine an abnormal device execution chain.

[0016] According to the abnormal device execution chain, multi-dimensional state feature information of each key device thereof is extracted to obtain abnormal risk evaluation information of each key device.

[0017] According to the abnormal risk evaluation information of each key device and in combination with past historical data of each key device, a risk device regulation instruction is output.

[0018] In a feasible scheme, the method for acquiring abnormal risk evaluation information comprises:

[0019] Based on geographical environment information of the target mountainous area and the information collection position of the target area, a dynamic interference screening model of the target mountainous area is constructed.

[0020] According to the dynamic interference screening model of the target mountainous area, effective data information of each device is screened to obtain data state credibility of each device.

[0021] Based on the data state credibility of each device, the effective data information of each device is screened to obtain state effective information of each device.

[0022] According to the state effective information of each device, fault feature probability extraction is performed to acquire a fault probability of each device.

[0023] According to the data state credibility of each device and the fault probability of each device and in combination with real-time traffic response information of each device, abnormal risk evaluation information of each device is determined.

[0024] In a feasible scheme, the method for acquiring the data state credibility of each device comprises:

[0025] Based on the data state credibility of each device and the fault probability of each device and in combination with real-time traffic response information of each device, abnormal risk evaluation information of each device is determined. The model performs credibility calculation on the effective data information of each device, specifically as follows:

[0026] Formula 1;

[0027] In formula 1, To assess the reliability of the data status, for Activation function index for time steps ( ), The time window length, As time step weights, This is the hidden state vector.

[0028] In one feasible approach, the method for obtaining the failure probability of each device includes:

[0029] Convolutional neural networks are used to extract spatial features of equipment signals and perform fault probability analysis. calculate:

[0030] Formula 2;

[0031] In Equation 2, For the first The activation values ​​of each convolutional feature map. For the first The weights of the fully connected layer corresponding to each feature The total number of feature dimensions. It is the base of the natural logarithm.

[0032] In one feasible approach, the method for determining the anomaly risk assessment information for each device includes:

[0033] Data status reliability based on each device and the failure probability of each device Calculate the abnormal risk assessment score for each device. :

[0034] Formula 3;

[0035] In Equation 3, This represents the number of traffic events within the current time window. For the first Attention weighting for each traffic incident For the first Risk vector value of a traffic incident , , Data status reliability for each device Failure probability The weighting of real-time traffic response information for each device.

[0036] In one feasible approach, the method for obtaining the overall state assessment information of each device execution chain includes:

[0037] Equation 4;

[0038] In Equation 4, Calculate the overall risk score for the chain for any device. The number of devices within the equipment execution chain. For the first The contribution weight of each key piece of equipment in the equipment execution chain For the first Reliability of data status for key equipment For the first Failure probability of key equipment For the first Real-time traffic response scores for key equipment. , , They are respectively , , The weight of the three, The number of interaction paths executed by the device within the chain. For the first The association strength of the interaction paths, This is an interactive adjustment coefficient that can be dynamically adjusted based on the complexity of the equipment execution chain. This is an interactive influencing factor.

[0039] In a second aspect, the present invention provides a monitoring system for the operation of electromechanical equipment and facilities on mountain highways, employing a monitoring method for the operation of electromechanical equipment and facilities on mountain highways as described in any one of the first aspects, wherein the monitoring system further includes:

[0040] The information acquisition module is used to collect status data information of each device in real time;

[0041] A data processing module, electrically connected to the information acquisition module, processes the status data information of each device;

[0042] A feature extraction module, electrically connected to the data processing module, extracts multi-dimensional state feature information of each device;

[0043] A risk assessment module, which is connected to a feature extraction module, is used to generate abnormal risk assessment information for each device.

[0044] A pre-regulation instruction output module is connected with the risk assessment module, and is configured to output a risk device pre-regulation instruction according to the abnormal risk assessment information of each device and in combination with the past historical data of each key device.

[0045] The present application has the following advantages:

[0046] The present application can effectively determine whether the monitored device in the region needs to be regulated in advance by evaluating the abnormal risk of each device in combination with the historical operation data of the device, and output corresponding pre-regulation instructions to prevent potential failures and ensure the stable operation of the mechanical and electrical equipment facilities of the mountainous highway. That is, the present application not only improves the accuracy of monitoring the highway equipment, but also greatly enhances the reliability and safety of the equipment operation. Meanwhile, the monitoring strategy and pre-regulation instructions can be continuously adjusted according to the actual operation situation to adapt to the complex and changeable operation environment of the mountainous highway. BRIEF DESCRIPTION OF DRAWINGS

[0047] Fig. 1 FIG. 1 is a schematic diagram of the overall process of the mountainous highway mechanical and electrical equipment facility operation monitoring method provided in the embodiments of the present application;

[0048] Fig. 2 FIG. 2 is a schematic diagram of the device execution chain regulation process in the mountainous highway mechanical and electrical equipment facility operation monitoring method provided in the embodiments of the present application. DETAILED DESCRIPTION

[0049] The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present application.

[0050] If the description of "first", "second", etc. is involved in the embodiments of the present application, the description of "first", "second", etc. is only for the purpose of description, and cannot be understood as indicating or implying the relative importance of the indicated technical features or implicitly indicating the number of the indicated technical features. Therefore, the features limited by "first", "second" can explicitly or implicitly include at least one of the features. In addition, the meaning of "and / or" appearing throughout the text includes three parallel solutions. Taking "A and / or B" as an example, it includes A solution, or B solution, or A and B solutions. In addition, the technical solutions of each embodiment can be combined with each other, but it must be based on the realization of ordinary skilled in the art. When the combination of technical solutions appears contradictory or unachievable, it should be considered that the combination of technical solutions does not exist, and is not within the scope of protection claimed by the present application.

[0051] Referring to Figs. 1-2 , the present application is to solve the problem that the operation state of mountainous area equipment and facilities cannot be monitored in time and effectively in the prior art, and provides a mountainous area highway electromechanical equipment and facility operation monitoring method. The present application can effectively determine whether the monitored equipment in the region needs to be regulated in advance by evaluating the abnormal risk of each equipment and combining the historical operation data of the equipment, and output corresponding pre-regulation instructions to prevent potential faults and ensure the stable operation of mountainous area highway electromechanical equipment and facilities. That is, the present application not only improves the accuracy of highway equipment monitoring, but also greatly enhances the reliability and safety of equipment operation. At the same time, the monitoring strategy and pre-regulation instructions can be continuously adjusted according to the actual operation situation to adapt to the complex and changeable operation environment of mountainous area highways.

[0052] Specifically, the present application provides a mountainous area highway electromechanical equipment and facility operation monitoring method in the first aspect, which comprises: the geographical position (including latitude, longitude, altitude, etc.) of the monitored mountainous area can be obtained in advance, and the distribution of each equipment in the mountainous area can be obtained, so as to construct the information collection position of the target region according to the geographical environment information of the target mountainous area, such as determining the position dimension and environment monitoring point of each equipment or each road section in the target mountainous area. Then, the state data information of each equipment can be collected in real time, including the environmental state data of equipment operation (such as temperature, humidity, wind speed, vibration influence caused by slope), equipment state response data (such as substation voltage, lighting system power, tunnel ventilation fan speed, etc.), and traffic state response data in the mountainous area (such as vehicle flow detection, abnormal event detection). Then, the state data information of each equipment can be processed according to the information collection position of the target region to obtain the effective data information of each equipment; that is, in order to facilitate subsequent data processing, the state data information of each equipment collected in real time can be filtered and cleaned and normalized to scale fusion, that is, the following formula can be used for data normalization processing:

[0053] ;

[0054] In the formula, is the original data, is the mean value of the state data, is the standard deviation, so as to fuse different state data under a unified scale.

[0055] After the scale fusion of the state data information of each device is performed, the effective data information of each device is obtained, and then the multi-dimensional feature extraction is performed on the effective data information of each device to obtain the multi-dimensional state feature information of each device (such as the credibility of different multi-source information sources in each device and the probability of the device that may show a fault); then the real-time traffic data of the target mountainous area can be collected in real time, and the abnormal risk assessment information of each device can be generated in combination with the multi-dimensional state feature information of each device; then finally, the risk device pre-control instruction can be output according to the abnormal risk assessment information of each device in combination with the past historical data of each key device. That is, in the embodiment, by evaluating the abnormal risk of each device in combination with the historical operation data of the device, whether the monitored device in the region needs to be controlled in advance can be effectively judged, and the corresponding pre-control instruction can be output to prevent the occurrence of potential faults and ensure the stable operation of the mountainous highway mechanical and electrical equipment facilities. That is, the present application not only improves the accuracy of the highway equipment monitoring, but also greatly enhances the reliability and safety of the equipment operation. At the same time, the monitoring strategy and the pre-control instruction can be continuously adjusted according to the actual operation situation to adapt to the complex and changeable operation environment of the mountainous highway.

[0056] In the embodiment, in order to facilitate understanding how to obtain the abnormal risk assessment information of each device, the following is explained. The method for obtaining the abnormal risk assessment information includes:

[0057] Based on the geographical environment information of the target mountainous area and the information collection location of the target area, a dynamic interference screening model for the target mountainous area is constructed. This model allows for in-depth analysis and screening of the effective data information of each device. It comprehensively considers the potential interference from geographical environmental factors (such as terrain undulation and climate conditions) on equipment operation, as well as the characteristics of the information collection location, thereby accurately identifying the effective components and potential interferences in the data of each device. The model then filters the effective data information of each device to obtain the data status credibility of each device. Based on this credibility, the effective data information of each device is further filtered and refined to obtain the effective status information of each device, ensuring the accuracy of subsequent fault analysis and risk assessment. Furthermore, fault-related feature patterns can be mined from the equipment operation data, and the probability of these patterns occurring can be calculated to obtain the fault probability of each device. Based on the data status credibility and fault probability of each device, combined with real-time traffic response information (such as the impact of traffic flow and abnormal events on equipment operation), a comprehensive analysis and calculation are performed to determine the abnormal risk assessment information for each device. This approach comprehensively considers multiple factors affecting equipment operation, accurately reflecting the current level of abnormal risk and providing strong support for subsequent pre-control commands. Specifically, in this embodiment, by constructing a dynamic interference screening model and performing multi-dimensional feature analysis on equipment data based on this model, abnormal characteristics of equipment operation in mountainous environments can be accurately obtained. That is, firstly, utilizing... The model processes effective data from the equipment, assigning weights at time steps and calculating hidden state vectors to obtain data state reliability reflecting the intensity of environmental interference. Subsequently, a convolutional neural network is used to extract spatial features of the equipment signals, and the failure probability is calculated by combining the weights of the fully connected layers. Finally, a weighted fusion of data state reliability, failure probability, and real-time traffic response information is used to form an anomaly risk assessment score that includes a traffic event attention mechanism and risk vector values. This multi-dimensional assessment method overcomes the limitations of traditional fixed-threshold monitoring. It can adapt to different traffic flows and geographical environments by dynamically adjusting weight parameters, and it can optimize pre-control instructions using historical operational data. This achieves a shift from a passive response to a proactive prevention monitoring mode, significantly improving the stability and safety of electromechanical equipment operation on mountainous highways.

[0058] Specifically, in order to adapt the reliability of equipment data in different latitude regions and reduce the impact of regional environmental factors on equipment operation data, the method for obtaining the data status reliability of each device includes:

[0059] Based on The model calculates the credibility of the valid data information for each device, as follows:

[0060] Formula 1;

[0061] In Equation 1, To assess the reliability of the data status, for Activation function, where, That is, by compressing the linear weighted sum to Intervals, transformed into probabilistic interpretations. index for time steps ( ), The time window length, As time step weights, This is the hidden state vector. That is, after normalizing all the original signals using a normalization formula and then scaling them together, they are concatenated into a multi-dimensional time-series vector. , The number of data dimension types (such as slope vibration, wind load fluctuation, temperature and humidity, etc.). The input window length represents the past duration. At this point, [the input window length is used]. The model performs time-series modeling of dynamic disturbance sequences caused by mountainous terrain (such as slope vibration, wind load fluctuations, and temperature and humidity analysis environmental dimensions), outputting environmental anomalies and providing environmental risk components for subsequent comprehensive risk assessment. This enables the model not only to detect current environmental anomalies but also to predict the changing trends of terrain-meteorological coupled disturbances, thus achieving early warning.

[0062] Specifically, in this embodiment, in order to extract spatial features from each device, the method for obtaining the failure probability of each device includes:

[0063] Convolutional neural networks are used to extract spatial features of equipment signals and perform fault probability analysis. calculate:

[0064] Formula 2;

[0065] In Equation 2, For the first The activation values ​​of each convolutional feature map. For the first The weights of the fully connected layer corresponding to each feature The total number of feature dimensions. It is the base of the natural logarithm.

[0066] This means that a convolutional neural network can be used to extract spatial features from multi-dimensional signals (such as vibration signals, current signals, temperature signals, etc.) generated during equipment operation. The extracted feature map activation values ​​are then weighted and summed with the corresponding fully connected layer weights, and then processed... Function transformation maps the result to interval, thereby obtaining the failure probability of the device. In this way, the spatial information in the device signal can be fully utilized, the accuracy of the failure probability calculation can be effectively improved, and reliable basis can be provided for subsequent risk assessment and device regulation. Meanwhile, in combination with the data state reliability obtained in the foregoing and the real-time response information of the device, abnormal risk assessment information of each device is determined, and then precise monitoring and early warning of the operation state of the mountainous highway electromechanical device and facility are realized. For example, the failure probability of the electromechanical facility can be extracted by means of spatial features such as voltage waveform distortion and power spectrum mutation, and weights corresponding to different spatial features are configured according to actual conditions, so as to realize determination of the current failure possibility of the electromechanical facility.

[0067] Specifically, in order to realize multi-dimensional abnormal risk assessment of the device, the method for determining the abnormal risk assessment information of each device comprises:

[0068] based on the data state reliability of each device and the failure probability of each device , calculating the abnormal risk assessment score of each device :

[0069] Formula 3

[0070] In formula 3, is the number of traffic events in the current time window, so as to dynamically adapt to different flow fluctuations; is the attention weight of the th traffic event, is the risk vector value of the th traffic event, , , respectively are the weight of the data state reliability of each device, the weight of the failure probability of each device and the weight of the real-time traffic response information of each device. That is, in this embodiment, the abnormal risk of each device can be comprehensively and accurately assessed by comprehensively considering the data state reliability, the failure probability and the real-time traffic response information of the device in multiple dimensions. Among them, the data state reliability reflects the data reliability of the device in a specific geographical environment, the failure probability reflects the possibility of failure of the device itself, and the real-time traffic response information considers the influence of traffic conditions on the operation of the device. In actual application, the values of , , may be adjusted according to actual conditions. For example, when the traffic flow of the mountainous highway is large and the traffic events are frequent, the values of to highlight the influence of real-time traffic response information on abnormal risk assessment; when the geographical environment of the device is complex and there are many interference factors, the value of the parameter can be appropriately increased to emphasize the importance of data state credibility.

[0071] In a feasible scheme, in order to save monitoring cost and reduce the computing power of monitoring operation, the monitoring method further comprises: acquiring at least one device execution chain according to the geographical environment information of the target mountainous area and in combination with the information collection position of the target area; wherein the device execution chain comprises an execution unit composed of multiple devices; (such as upstream and downstream devices that support each other in a certain section, such as execution device-power device-power supply device-central control device. Such as ventilation fan, ventilation power source, power supply facility, wind speed regulation facility; such as lighting lamp, lighting power supply device, lighting regulation device, etc.). Then, the overall state of each device execution chain is evaluated to obtain the overall state evaluation information of each device execution chain.

[0072] ​Then the overall state evaluation information of the device execution chain can be compared with the preset chain state evaluation threshold to determine an abnormal device execution chain. For subsequent positioning and regulation of the abnormal device condition of the abnormal device execution chain, the multi-dimensional state feature information of each key device of the abnormal device execution chain can be extracted to obtain abnormal risk evaluation information of each key device. Then, according to the abnormal risk evaluation information of each key device and in combination with the past historical data of each key device, a risk device regulation instruction is output. That is, in the embodiment, when the device execution chain is obtained, the physical connection relationship, the functional dependency relationship and the data interaction relationship among the devices need to be comprehensively considered. For example, in a tunnel ventilation system, a ventilation fan serves as an execution device, and its running state is directly affected by a ventilation power source, while the power source depends on the stable power supply of a power supply device, and a central control device is responsible for overall regulation. The four constitute a complete device execution chain. By constructing such a chain model, the running state of the device can be evaluated from the system level, and misjudgment caused by isolated analysis of a single device can be avoided. For an abnormal device execution chain, the multi-dimensional state features of the key devices in the chain are extracted, including device vibration spectrum analysis, current fluctuation curve, temperature change trend, etc., and a device health record is constructed in combination with historical operation data. The machine learning algorithm is used to recognize the pattern of the feature data to accurately locate the fault source device. For example, in a lighting system, if the voltage fluctuation of a certain line is detected to be abnormal and the temperature of the lamp is continuously rising, the system can judge that the power supply device is in poor contact or the line is aging. The generated regulation instruction can finally contain a three-level response mechanism: primary warning is achieved by adjusting the device running parameters, such as reducing the speed of the ventilation fan to reduce the load; intermediate intervention needs to start the standby device to form redundant support, such as switching to a standby power supply line; in an emergency, a safety protection program is triggered, such as forcibly shutting down the faulty device and starting the emergency lighting system. All regulation instructions are attached with priority identification and execution time limit to ensure that the basic functions can still be maintained under complex working conditions. The device maintenance is changed from passive repair to active prevention.

[0073] In the embodiment, in order to facilitate understanding of how to obtain the overall state evaluation information of each device execution chain, the following is described. The method for obtaining the overall state evaluation information of each device execution chain comprises:

[0074] Formula 4;

[0075] In formula 4, is the overall risk score of any device execution chain, is the number of devices in the device execution chain, is the contribution weight of the th key device in the device execution chain (which can be preset ), is the abnormal risk evaluation information of the

[0074] th key device. Data state credibility of the key device (which can be calculated according to formula 1), Failure probability of the first key device, Real-time traffic response score of the first key device, 、 、 Weight of the three respectively, 、 、 Interaction path number in the device execution chain, Association strength of the first interaction path, Interaction adjustment coefficient, which can be dynamically adjusted according to the complexity of the device execution chain, Interaction influence factor, which can be calculated based on historical linkage failure data, that is, The linkage occurrence rate in the historical failure data can be used as a benchmark value. That is, in the embodiment, the overall risk score of the device execution chain can be accurately calculated, which provides a key basis for subsequent abnormality judgment and control instruction output. In actual application, the overall risk score of the device execution chain obtained by calculation can be compared with a preset threshold value. If the overall risk score exceeds the threshold value, it is determined that the device execution chain has an abnormality, and then the corresponding control mechanism is triggered. At the same time, according to the specific situation of the abnormality, the multi-dimensional state feature information of each key device in the device execution chain can be extracted and analyzed again to determine the abnormal risk assessment information of each key device. That is, by combining the past historical data of each key device, more accurate risk device control instructions can be output, so as to ensure the safe and stable operation of the mountainous highway mechanical and electrical equipment and facilities. It should be noted that the risk device control instructions include but are not limited to: power load reduction, standby device switching, maintenance priority sorting and remote parameter resetting.

[0076] ​In order to solve the above-mentioned shortcomings in the prior art that the running state of the equipment and facilities in the mountainous area cannot be monitored in time and effectively, the present application also provides a mountainous highway electromechanical equipment and facility operation monitoring system in the second aspect, which adopts the mountainous highway electromechanical equipment and facility operation monitoring method of any one of the first aspect, and the monitoring system further comprises an information acquisition module, a data processing module, a feature extraction module, a risk assessment module and a pre-control instruction output module. The information acquisition module is used for acquiring the state data information of each equipment in real time; the data processing module is electrically connected with the information acquisition module, and the data processing module processes the state data information of each equipment; the feature extraction module is electrically connected with the data processing module, and the feature extraction module extracts the multi-dimensional state feature information of each equipment; the risk assessment module is connected with the feature extraction module, and the risk assessment module is used for generating abnormal risk assessment information of each equipment; and the pre-control instruction output module is connected with the risk assessment module, and is used for outputting a risk equipment pre-control instruction according to the abnormal risk assessment information of each equipment and combining the past historical data of each key equipment. That is, in the embodiment, the monitoring system realizes comprehensive monitoring and intelligent control of the running state of the mountainous highway electromechanical equipment and facilities through the cooperative work of the modules. The information acquisition module can cover key equipment points by using a high-precision sensor network, capture multi-dimensional operation parameters such as vibration, temperature and current in real time, and ensure the stability of data transmission through an anti-interference communication protocol. The data processing module uses a built-in dynamic interference filtering algorithm to clean and normalize the original data, eliminate the influence of the complex environment in the mountainous area (such as strong electromagnetic interference and sudden changes in temperature and humidity) on signal quality, and provide a reliable data basis for subsequent analysis. Through the feature extraction module, LSTM time sequence modeling and convolutional neural network spatial feature analysis technology are combined to deeply mine the equipment health state features from the processed data, and form a feature vector set containing time dimension evolution law and spatial correlation characteristics. Then, the risk assessment module generates a quantitative risk score based on a multi-dimensional feature fusion model by calculating the data state reliability, fault probability and traffic response factor through weighted calculation, and dynamically adapts the evaluation weight under different geographical environments and traffic flow scenarios.

[0077] In some embodiments, the monitoring system can communicate using any currently known or future developed network protocol, such as HTTP (Hyper Text Transfer Protocol), and can be interconnected with digital data communication (e.g., a communication network) of any form or medium. Examples of communication networks include local area networks (“LAN”), wide area networks (“WAN”), internetworks (e.g., the Internet), and peer-to-peer networks (e.g., ad hoc peer-to-peer networks), as well as any currently known or future developed networks.

[0078] The functionality described herein above can be performed, at least in part, by one or more hardware logic components. For example, and without limitation, illustrative types of hardware logic components that can be used include Field-programmable Gate Arrays (FPGAs), Program-specific Integrated Circuits (ASICs), Program-specific Standard Products (ASSPs), System-on-a-chip systems (SOCs), Complex Programmable Logic Devices (CPLDs), etc.

[0079] A third aspect of the present application provides a computer readable medium having stored thereon a computer program, wherein the program, when executed by a processor, implements the mountainous highway electromechanical equipment and facility operation monitoring method according to any one of the first aspect. The computer readable medium in the embodiment can be written in one or more programming languages or combinations thereof for executing computer program codes that perform the operations of some embodiments of the present disclosure, including object-oriented programming languages such as Java, Smalltalk, C++, and conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on a user computer, partially on a user computer, as an independent software package, partially on a user computer and partially on a remote computer, or entirely on a remote computer or server. In the case involving a remote computer, the remote computer can be connected to the user computer through any kind of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (for example, through the Internet using an Internet service provider).

[0080] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functionalities, and operations of possible implementations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flow diagrams or block diagrams can represent a module, a segment, or a portion of code, which comprises one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently or in the reverse order, depending on the functionality involved. It will also be noted that each block in the block diagrams and / or flow diagrams, and combinations of blocks in the block diagrams and / or flow diagrams, can be implemented by special-purpose hardware-based systems that perform the specified functions or operations, or combinations of special-purpose hardware and computer instructions.

[0081] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program according to some embodiments of the present disclosure. For example, some embodiments of the present disclosure include a computer program product comprising a computer program carried on a computer readable medium, the computer program comprising program code for performing the methods illustrated by the flowcharts.

[0082] The fourth aspect of the present application provides an electronic device, comprising: one or more processors; a memory device having one or more programs stored thereon; when the one or more programs are executed by the one or more processors, the one or more processors implement the mountainous highway electromechanical equipment facility operation monitoring method according to the first aspect. Wherein, the computer readable medium can be included in the electronic device, or can exist separately, i.e. not assembled into the electronic device. The computer readable medium carries one or more programs, when the one or more programs are executed by the electronic device, the electronic device can implement the mountainous highway electromechanical equipment facility operation monitoring method according to the first aspect.

[0083] The fifth aspect of the present application provides a computer program product, comprising a computer program, when the computer program is executed by a processor, the mountainous highway electromechanical equipment facility operation monitoring method according to the first aspect is implemented.

[0084] The above description is only some preferred embodiments of the present disclosure and the explanation of the applied technical principles. Those skilled in the art should understand that the scope of the application involved in the embodiments of the present disclosure is not limited to the technical solutions formed by the specific combinations of the above technical features, and should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features and the technical features disclosed in the embodiments of the present disclosure (but not limited to) with similar functions are replaced with each other to form a technical solution.

Claims

1. A method for monitoring the operation of electromechanical equipment and facilities on mountain highways, characterized in that, include: Based on the geographical environment information of the target mountainous area and the information collection location of the target area, obtain at least one device execution chain; The device execution chain includes: an execution unit composed of multiple devices; Perform an overall status assessment on each device execution chain to obtain overall status assessment information for each device execution chain; The overall status assessment information of the equipment execution chain is compared with the preset chain status assessment threshold to identify abnormal equipment execution chains. Based on the execution chain of the abnormal equipment, multi-dimensional state feature information of each key equipment is extracted to obtain the abnormal risk assessment information of each key equipment. Based on the abnormal risk assessment information of each key piece of equipment, and combined with the historical data of each key piece of equipment, control instructions for the risky equipment are output; The methods for obtaining abnormal risk assessment information include: Based on the geographical environment information of the target mountain area and the information collection location of the target area, a dynamic interference screening model for the target mountain area is constructed. Based on the dynamic interference screening model of the target mountain area, the effective data information of each device is screened to obtain the data status credibility of each device. Based on the data status reliability of each device, the effective data information of each device is filtered to obtain the effective status information of each device. Based on the valid status information of each device, fault feature probability is extracted to obtain the fault probability of each device; Based on the data status reliability and failure probability of each device, and combined with the real-time traffic response information of each device, the abnormal risk assessment information of each device is determined. Specifically, the method for obtaining the overall state assessment information of each device execution chain includes: Equation 4; In Equation 4, Calculate the overall risk score for the chain for any device. The number of devices within the execution chain. For the first The contribution weight of each key piece of equipment in the equipment execution chain For the first Reliability of data status for key equipment For the first Failure probability of key equipment For the first Real-time traffic response scores for key equipment. , , They are respectively , , The weight of the three, The number of interaction paths executed by the device within the chain. For the first The association strength of the interaction paths, This is an interactive adjustment coefficient that can be dynamically adjusted based on the complexity of the equipment execution chain. This is an interactive influencing factor.

2. The method for monitoring the operation of electromechanical equipment and facilities on a mountain highway according to claim 1, characterized in that, The method for obtaining the data status reliability of each device includes: based on The model calculates the credibility of the valid data information for each device, as follows: Formula 1; In Equation 1, To assess the reliability of the data status, for Activation function index for time steps ( ), The time window length, As time step weights, This is the hidden state vector.

3. The method for monitoring the operation of electromechanical equipment and facilities on a mountain highway according to claim 2, characterized in that, The method for obtaining the failure probability of each device includes: Convolutional neural networks are used to extract spatial features of equipment signals and perform fault probability analysis. calculate: Formula 2; In Equation 2, For the first The activation values ​​of each convolutional feature map. For the first The weights of the fully connected layer corresponding to each feature The total number of feature dimensions. It is the base of the natural logarithm.

4. The method for monitoring the operation of electromechanical equipment and facilities on a mountain highway according to claim 3, characterized in that, The method for determining the abnormal risk assessment information for each device includes: Data status reliability based on each device and the failure probability of each device Calculate the abnormal risk assessment score for each device. : Formula 3; In Equation 3, This represents the number of traffic events within the current time window. For the first Attention weighting for each traffic incident For the first Risk vector value of a traffic incident , , Data status reliability for each device Failure probability The weighting of real-time traffic response information for each device.

5. A monitoring system for the operation of electromechanical equipment and facilities on a mountain highway, characterized in that, The method for monitoring the operation of electromechanical equipment and facilities on mountain highways, as described in any one of claims 1 to 4, is adopted.

Images