Method, device, equipment and medium for processing running state of electric special vehicle

Abstract

The present disclosure relates to the technical field of power systems, and particularly relates to a kind of operation state processing method, device, equipment and medium of electric power special vehicle, the method comprises: obtaining each single index in the classical domain and the section domain of preset state risk level, and the measured index value of each single index;According to the classical domain and the section domain of single index in the preset state risk level, and the measured index value of single index, the first correlation degree of single index and each state risk level is calculated;The state risk level of the highest first correlation degree is taken as the state risk level of single index;Based on the first correlation degree of each single index and each state risk level, the state risk level of each function module and the state risk level of electric power special vehicle are determined.The technical scheme can improve the intelligent operation and maintenance capability of electric power special vehicle, realize comprehensive, real-time, accurate monitoring to vehicle operation state, and is mainly used for the state monitoring of electric power special vehicle.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of power systems, and in particular to a method and device for processing the running state of a power special vehicle, equipment and a medium. BACKGROUND

[0002] With the accelerated promotion of global energy transformation and smart grid construction, the demand for power special vehicles has surged, becoming an important tool for power grid operation, repair and emergency handling. However, the digital capabilities of current power special vehicles are generally insufficient and need to be upgraded. In the prior art, the monitoring means of power special vehicles are relatively backward, mainly relying on manual inspection and simple sensor monitoring. These methods are not only inefficient, but also difficult to achieve comprehensive, real-time and accurate monitoring of the running state of the vehicle. SUMMARY

[0003] To solve the problems in the related art, the present disclosure provides a method and device for processing the running state of a power special vehicle, equipment and a medium.

[0004] In a first aspect, the present disclosure provides a method for processing the running state of a power special vehicle, comprising:

[0005] obtaining the classical domain and the sector domain of each single index of the power special vehicle at a preset state risk level, the power special vehicle corresponding to a plurality of functional modules, each functional module corresponding to a plurality of single indexes;

[0006] obtaining the measured index value of each single index;

[0007] For each single index, according to the classical domain and the sector domain of the single index at a preset state risk level, and the measured index value of the single index, calculating the first correlation degree of the single index and each state risk level;

[0008] The state risk level with the highest first correlation degree is taken as the state risk level of the single index;

[0009] Based on the first correlation degree of each single index and each state risk level, the state risk level of each functional module and the state risk level of the power special vehicle are determined.

[0010] In a possible implementation, the determination of the state risk level of each functional module and the state risk level of the power special vehicle based on the first correlation degree of each single index and each state risk level comprises:

[0011] For each functional module, based on the first correlation degree of the plurality of single indexes corresponding to the functional module and each state risk level, the second correlation degree of the functional module and each state risk level is determined.

[0012] Using the state risk level with the second highest correlation as the state risk level of the functional module;

[0013] Determining a third degree of association between the electric special vehicle and each state risk level based on the second degree of association between each functional module and each state risk level;

[0014] The state risk level with the third highest correlation degree is used as the state risk level of the electric special vehicle.

[0015] In a possible implementation, calculating the first correlation between the single indicator and each state risk level based on the single indicator in the preset classical domain and section domain of the state risk level and the measured indicator value of the single indicator includes:

[0016] Calculate the i-th single indicator s according to the following formula i The first correlation degree with the k-th level of state risk

[0017]

[0018] in, and Each single indicator is s i The lower and upper thresholds of the classic domain of the k-th state risk level, a i and b i Each single indicator is s i The lower and upper thresholds of the section domain, i > for the single indicator s i The measured index value.

[0019] In a possible implementation, determining the second correlation between the functional module and each state risk level based on the first correlation between the multiple single indicators corresponding to the functional module and each state risk level includes:

[0020] Using a hierarchical analysis method, a first judgment matrix corresponding to the functional module is obtained, and a basic weight of each single indicator in the functional module is calculated based on the first judgment matrix, wherein the first judgment matrix is ​​used to represent a comparison value of the importance between multiple single indicators in the functional module;

[0021] The basic weights of the single indicators are modified by using a variable weight comprehensive model based on factor space theory to obtain the variable weight vectors of the single indicators in the functional module;

[0022] ​Based on the variable weight vector and the first correlation degrees between the plurality of single indicators corresponding to the functional modules and the risk levels of the respective states, a second correlation degree between the functional modules and the risk levels of the respective states is calculated.

[0023] In a possible implementation, the variable weight comprehensive model based on factor space theory is used to modify the basic weight of each single indicator to obtain the variable weight vector of each single indicator in the functional module, including:

[0024] According to the following formula, the number of the jth functional module is calculated The variable weight vector of a single indicator

[0025] in, is the total number of single indicators in the jth functional module, For the jth functional module The basic weight of a single indicator, i j > is the i-th single indicator s in the j-th functional module i j The measured index value, α is the preset value, a i j and b i j are the i-th single indicator s in the j-th functional module i j The upper and lower thresholds of the section domain.

[0026] In a possible implementation, calculating the second correlation between the functional module and each state risk level based on the variable weight vector and the first correlation between the plurality of single indicators corresponding to the functional module and each state risk level includes:

[0027] The second correlation between the jth functional module and the kth level of state risk is calculated according to the following formula:

[0028]

[0029] in, is the i-th single indicator s in the j-th functional module i j The first degree of association with the k-th state risk level.

[0030] In a possible implementation, determining the third degree of association between the electric special vehicle and each state risk level based on the second degree of association between each functional module and each state risk level includes: ​

[0031] obtaining a second judgment matrix corresponding to the electric special vehicle by using the analytic hierarchy process, and calculating a basic weight of each functional module in the electric special vehicle based on the second judgment matrix, wherein the second judgment matrix is used to represent comparison values of importance degrees between the plurality of functional modules in the electric special vehicle;

[0032] calculating a third correlation degree between the electric special vehicle and each state risk level based on the basic weight of each functional module in the electric special vehicle and the second correlation degree between each functional module and each state risk level in the electric special vehicle.

[0033] In a possible implementation, the calculating the third correlation degree between the electric special vehicle and each state risk level based on the basic weight of each functional module in the electric special vehicle and the second correlation degree between each functional module and each state risk level in the electric special vehicle comprises:

[0034] The third correlation degree R between the electric special vehicle and the kth state risk level is calculated according to the following formula: k :

[0035]

[0036] wherein M2 is a total number of the functional modules in the electric special vehicle, w 0,j is the basic weight of the jth functional module in the electric special vehicle, is the second correlation degree between the jth functional module and the kth state risk level.

[0037] In a possible implementation, the method further comprises:

[0038] When the state risk level of the electric special vehicle is a risk level requiring operation and maintenance work, the state risk levels of each single indicator are input into a pre-trained identification model, the identification model is executed, and an operation and maintenance work type output by the identification model is obtained, wherein the operation and maintenance work type comprises edge-side operation and maintenance, cloud-side operation and maintenance, and cloud-edge collaborative operation and maintenance.

[0039] When the operation and maintenance work type is edge-side operation and maintenance, a first reminder information is output, and the first reminder information is used to remind edge-side personnel to perform operation and maintenance work.

[0040] When the operation and maintenance work type is cloud-side operation and maintenance, the state risk levels of each single indicator, the state risk levels of each functional module, and the state risk level of the electric special vehicle are sent to the cloud.

[0041] When the operation and maintenance type is the cloud-edge collaborative operation and maintenance, second reminding information is output to remind the edge personnel to perform operation and maintenance and to send the state risk levels of each single indicator of the electric special vehicle, the state risk levels of each functional module, and the state risk level of the electric special vehicle to the cloud.

[0042] In a second aspect, an operation state processing apparatus for an electric special vehicle is provided in the embodiments of the present disclosure, and the operation state processing apparatus comprises:

[0043] A first obtaining module is configured to obtain a classical domain and a section domain of a preset state risk level of each single indicator of an electric special vehicle, the electric special vehicle corresponding to a plurality of functional modules, and each functional module corresponding to a plurality of single indicators;

[0044] A second obtaining module is configured to obtain a measured indicator value of each single indicator;

[0045] A calculating module is configured to, for each single indicator, calculate a first correlation degree between the single indicator and each state risk level according to the classical domain and the section domain of the preset state risk level of the single indicator and the measured indicator value of the single indicator;

[0046] A first level determining module is configured to take a state risk level with the highest first correlation degree as a state risk level of the single indicator;

[0047] A second level determining module is configured to determine a state risk level of each functional module and a state risk level of the electric special vehicle based on the first correlation degree between each single indicator and each state risk level.

[0048] In a possible implementation, the second level determining module is configured to:

[0049] For each functional module, determine a second correlation degree between the functional module and each state risk level based on the first correlation degree between the plurality of single indicators corresponding to the functional module and each state risk level;

[0050] take a state risk level with the highest second correlation degree as a state risk level of the functional module;

[0051] determine a third correlation degree between the electric special vehicle and each state risk level based on the second correlation degree between each functional module and each state risk level;

[0052] take a state risk level with the highest third correlation degree as a state risk level of the electric special vehicle.

[0053] In a possible implementation, the calculating module is configured to:

[0054] Calculate the i-th single indicator s according to the following formula i The first correlation degree with the k-th level of state risk

[0055]

[0056] in, and They are single indicators s i The lower and upper thresholds of the classic domain of the k-th state risk level, a i and b i Each single indicator is s i The lower and upper thresholds of the section domain, i > for the single indicator s i The measured index value.

[0057] In a possible implementation, the portion of the second level determination module that determines the second degree of association between the functional module and each state risk level based on the first degree of association between the multiple single indicators corresponding to the functional module and each state risk level is configured as follows:

[0058] Using a hierarchical analysis method, a first judgment matrix corresponding to the functional module is obtained, and a basic weight of each single indicator in the functional module is calculated based on the first judgment matrix, wherein the first judgment matrix is ​​used to represent a comparison value of the importance between multiple single indicators in the functional module;

[0059] The basic weights of the single indicators are modified by using a variable weight comprehensive model based on factor space theory to obtain the variable weight vectors of the single indicators in the functional module;

[0060] Based on the variable weight vector and the first correlation degrees between the plurality of single indicators corresponding to the functional modules and the risk levels of the respective states, a second correlation degree between the functional modules and the risk levels of the respective states is calculated.

[0061] In one possible implementation, the second level determination module uses a variable weight comprehensive model based on factor space theory to modify the basic weights of the single indicators, and the part that obtains the variable weight vector of each single indicator in the functional module is configured as follows:

[0062] According to the following formula, the number of the jth functional module is calculated The variable weight vector of a single indicator

[0063] in, is the total number of single indicators in the jth functional module, ​a measured value of the i th single index s a preset value, a i j a measured value of the i th single index s i j in the j th functional module, a i j and b i j upper and lower threshold values of a section of the i th single index s i j in the j th functional module.

[0064] In a possible implementation, the part of the second level determination module that calculates the second association degrees of the functional modules and the state risk levels based on the variable weight vector and the first association degrees of the functional modules and the state risk levels is configured to:

[0065] calculate the second association degree of the j th functional module and the k th state risk level according to the following formula

[0066]

[0067] wherein, a measured value of the i th single index s i j and the k th state risk level.

[0068] In a possible implementation, the part of the second level determination module that determines the third association degrees of the electric special vehicle and the state risk levels based on the second association degrees of each functional module and the state risk levels is configured to:

[0069] obtain a second judgment matrix corresponding to the electric special vehicle by using the analytic hierarchy process, and calculate the basic weights of the functional modules in the electric special vehicle based on the second judgment matrix, wherein the second judgment matrix is used to represent comparison values of importance degrees between the functional modules in the electric special vehicle;

[0070] calculate the third association degrees of the electric special vehicle and the state risk levels based on the basic weights of the functional modules in the electric special vehicle and the second association degrees of the functional modules in the electric special vehicle and the state risk levels.

[0071] In a possible implementation, the second level determination module is configured to calculate the third correlation degree of the power special vehicle and the state risk level based on the basic weight of each functional module in the power special vehicle and the second correlation degree of each functional module in the power special vehicle and each state risk level, and the part is configured to:

[0072] The third correlation degree of the power special vehicle and the kth state risk level is calculated according to the following formula: k :

[0073]

[0074] wherein M2 is the total number of functional modules in the power special vehicle, w 0,j is the basic weight of the jth functional module in the power special vehicle, is the second correlation degree of the jth functional module and the kth state risk level.

[0075] In a possible implementation, the apparatus further includes:

[0076] The type identification module is configured to, when the state risk level of the power special vehicle is the risk level requiring operation and maintenance work, input the state risk level of each single indicator into a pre-trained identification model, execute the identification model, and obtain an operation and maintenance work type output by the identification model, the operation and maintenance work type including side operation and maintenance, cloud-side operation and maintenance, and cloud-side collaborative operation and maintenance.

[0077] The output module is configured to, when the operation and maintenance work type is side operation and maintenance, output first reminding information, the first reminding information being used to remind side personnel to perform operation and maintenance work; when the operation and maintenance work type is cloud-side operation and maintenance, send the state risk level of each single indicator of the power special vehicle, the state risk level of each functional module, and the state risk level of the power special vehicle to the cloud; and when the operation and maintenance work type is cloud-side collaborative operation and maintenance, output second reminding information to remind side personnel to perform operation and maintenance work and send the state risk level of each single indicator of the power special vehicle, the state risk level of each functional module, and the state risk level of the power special vehicle to the cloud.

[0078] In a third aspect, an electronic device is provided, including a memory and a processor, wherein the memory is configured to store one or more computer instructions, and the one or more computer instructions are executed by the processor to implement the method in any one of the first aspect.

[0079] In a fourth aspect, the disclosure provides a computer readable storage medium having computer instructions stored thereon, the computer instructions being executed by a processor to implement the method of any one of the first aspect.

[0080] According to the technical solution provided by the disclosure, a multi-level evaluation system is provided, which integrates single indicators, function modules and operation state evaluation of electric special vehicles, and realizes multi-granularity state monitoring and evaluation from fine to coarse. Meanwhile, the embodiment fully utilizes the matter-element extension model, combines the operation state evaluation at each level, and uses the correlation degree of the matter-element extension model to represent the state risk level of the single indicator. Then, based on the first correlation degree between the single indicator and the state risk level, the state risk level of each function module and the state risk level of the electric special vehicle are determined. The operation state evaluation steps at each level are simplified, which can be conveniently deployed in the corresponding Internet of Things terminal of the electric special vehicle, thereby improving the intelligent operation and maintenance capability of the electric special vehicle, realizing comprehensive, real-time and accurate monitoring of the vehicle operation state, and realizing fault early warning, in-process monitoring and post-mortem based on the state risk level at each level.

[0081] It should be understood that the above general description and the following detailed description are only exemplary and explanatory, and cannot limit the disclosure. BRIEF DESCRIPTION OF DRAWINGS

[0082] Other features, objects and advantages of the disclosure will become more apparent from the following detailed description of the non-limiting embodiments, combined with the attached drawings. In the drawings:

[0083] Figure 1 A flow chart of an operation state processing method of an electric special vehicle is shown.

[0084] Figure 2 A schematic diagram of a multi-level operation state evaluation system is shown.

[0085] Figure 3 A structural block diagram of an operation state processing device of an electric special vehicle is shown.

[0086] Figure 4 A structural block diagram of an electronic device according to an embodiment of the disclosure is shown.

[0087] Figure 5 A structural schematic diagram of a computer system suitable for implementing the method of the embodiment of the disclosure is shown. DETAILED DESCRIPTION

[0088] Hereinafter, exemplary embodiments of the present disclosure will be described in detail with reference to the accompanying drawings so that those skilled in the art can easily implement them. In addition, for the sake of clarity, parts not related to the description of the exemplary embodiments are omitted in the accompanying drawings.

[0089] In the present disclosure, it should be understood that terms such as "include" or "have" are intended to indicate the presence of features, numbers, steps, actions, components, parts, or combinations thereof disclosed in the present specification, and are not intended to exclude the possibility that one or more other features, numbers, steps, actions, components, parts, or combinations thereof exist or are added.

[0090] It should also be noted that, in the absence of conflict, the embodiments and features of the embodiments of the present disclosure may be combined with each other. The present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0091] In order to solve the problems raised in the background technology, this embodiment proposes a multi-level evaluation system, which integrates single indicators, functional modules and operating status evaluation of electric special vehicles, and realizes multi-granularity status monitoring and evaluation from fine to coarse. At the same time, this embodiment makes full use of the physical element extension model, fully combines it with the operating status evaluation at all levels, and uses the correlation of the physical element extension model to characterize the status risk level of a single indicator. Then, based on the first correlation between the single indicator and each status risk level, the status risk level of each functional module and the status risk level of the electric special vehicle are determined, which simplifies the operating status evaluation steps at all levels and can be conveniently deployed in the Internet of Things terminal corresponding to the electric special vehicle, thereby improving the intelligent operation and maintenance capabilities of the electric special vehicle, realizing comprehensive, real-time and accurate monitoring of the vehicle's operating status, and realizing pre-fault warning, in-process monitoring and post-fault review based on the status risk levels at all levels.

[0092] In addition, this embodiment can also guide the subsequent operation and maintenance work of the vehicle based on the single indicator, each functional module and the status risk level of the electric special vehicle. When the status risk level of the electric special vehicle is a risk level that requires operation and maintenance work, the side IoT terminal can implement a side operation and maintenance work diversion strategy based on the status risk of the single indicator, determine the attribution of the operation and maintenance work, form a fault warning-operation and maintenance allocation closed loop, and realize accurate allocation of operation and maintenance work. The owner of the operation and maintenance work can perform operation and maintenance work based on the single indicator, each functional module and the status risk level of the electric special vehicle to achieve rapid response to faults.

[0093] Figure 1 FIG. 1 is a flow chart showing a method for processing the operating status of an electric special vehicle provided by an embodiment of the present disclosure. Figure 1 As shown, the method for processing the operating status of the electric special vehicle includes the following steps S101-S105:

[0094] In step S101, the classical domain and the section domain of each single index of the electric special vehicle corresponding to a plurality of functional modules, each functional module corresponding to a plurality of single indexes, in a preset state risk level are obtained.

[0095] In step S102, the measured index value of each single index is obtained.

[0096] In step S103, for each single index, the first correlation degree of the single index and each state risk level is calculated according to the classical domain and the section domain of the single index in a preset state risk level and the measured index value of the single index.

[0097] In step S104, the state risk level with the highest first correlation degree is taken as the state risk level of the single index.

[0098] In step S105, the state risk level of each functional module and the state risk level of the electric special vehicle are determined based on the first correlation degree of each single index and each state risk level.

[0099] In a possible implementation, the operation state processing method of the electric special vehicle can be used for a computer device capable of performing operation state processing of the electric special vehicle, such as an Internet of Things terminal installed on the electric special vehicle, or an Internet of Things terminal located near the electric special vehicle and capable of communicating with the electric special vehicle.

[0100] In a possible implementation, the electric special vehicle refers to a vehicle specially designed and equipped for specific tasks in the power industry, which plays an important role in ensuring power supply, emergency repair, equipment transportation, etc. For example, the electric special vehicle can be a mobile ring network cabinet vehicle, a mobile energy storage vehicle, a mobile power generation vehicle, etc.

[0101] In a possible implementation, for the operation and maintenance requirements and operation characteristics of the electric special vehicle, the embodiment proposes a multi-level operation state evaluation system, Figure 2 A schematic diagram of a multi-level operation state evaluation system provided by an embodiment of the present disclosure is shown in FIG. 1. Figure 2 As shown in FIG. 1, the multi-level operation state evaluation system includes three levels of operation state evaluation of the state of single indexes, the state of functional modules and the state of electric special vehicles. Each electric special vehicle corresponds to a plurality of functional modules, each functional module corresponds to a plurality of single indexes, and the state evaluation of the functional module in the middle can help the operation and maintenance personnel quickly locate the fault position and obtain the overall cognition of the state of the functional module, which is convenient for quick fault judgment and disposal.

[0102] In a possible implementation, the function module can be a plurality of modules according to the function division of the vehicle, and the single index is an index selected by experts in the field by studying the influencing factors of each function module, and following the principles of completeness, typicality, comparability, operability, quantifiability and the like. For example, for a mobile power generation vehicle, a plurality of function modules corresponding to the vehicle chassis, the generator set and the environmental monitoring module can be set. For the vehicle chassis, the following single indexes can be set: loading mass, distance from low point to ground, climbing angle, turning radius and the like. For the generator set, the following single indexes can be set: voltage, current, power, frequency, power generation capacity, circuit breaker opening and closing position, oil pressure, coolant temperature, working time, battery voltage and the like. These indexes are used to monitor and warn the abnormal faults of the generator set, such as coolant over-temperature, low oil level, overload, abnormal frequency, abnormal voltage and low battery voltage of the generator set, which helps the staff to deal with the faults on site. For the environmental monitoring module, the following single indexes can be set: temperature, humidity, vehicle position and the like. Of course, for other types of electric special vehicles, there can be other function modules, such as a mobile ring network cabinet vehicle, which can also correspond to a ring network cabinet module, a mobile energy storage vehicle, which can also correspond to an energy storage module, and the like, which will not be illustrated one by one here.

[0103] In a possible implementation, the preset state risk level can be preset by experts in the field based on actual conditions. For example, the state risk levels of the above-mentioned three running states can all be set to three levels: k = 1, 2, 3 correspond to three state risk levels, wherein k = 1 means "abnormal", k = 2 means "warning", and k = 3 means "normal". Of course, in other examples, the state risk levels of the above-mentioned three running states can also be set to four or more levels, such as "normal", "normal warning", "emergency warning" and "abnormal", and the like, which are not limited here.

[0104] In a possible implementation, the multi-level running state of the electric special vehicle can be evaluated by using a matter-element extension model. It is assumed that the electric special vehicle corresponds to M1 single indexes, wherein the i-th single index can be denoted as s i , i = 1,..., M1; the ranges of the classic field and the section field of each single index can be determined according to relevant technical specifications, expert knowledge and the like. It should be noted that in order to facilitate data processing, the upper and lower limits of the section field range can be used to normalize the section field, the classic field and the subsequent measured index values of the single index.

[0105] Here, the classical field refers to an important concept in the matter-element extension model. In the evaluation of the running state of a single indicator, each single indicator corresponds to a standard value range at each risk level according to the preset state risk level. This range is the classical field. The classical field of the above M1 single indicators can be expressed as:

[0106]

[0107] where N is the state risk level of the single indicator, S = s1, k M1 is the single indicator, Q k refers to the upper and lower threshold values of the classical field of the corresponding single indicator, for example, is the lower threshold value of the classical field of the single indicator s1 at the kth state risk level, is the upper threshold value of the classical field of the single indicator s1 at the kth state risk level.

[0108] The section field refers to the range of all possible values of the single indicator. By taking the union set A = A1∪A2∪A3 of the classical fields of the three state risk levels, it can be expressed as:

[0109]

[0110] where N is the set of state risk levels of the single indicator, S = s1, M1 is the single indicator, Q refers to the upper and lower threshold values of the section field of the corresponding single indicator, for example, a1 is the lower threshold value of the section field of the single indicator s1, and b1 is the upper threshold value of the section field of the single indicator s1.

[0111] In one possible implementation, the measured indicator values of M1 single indicators can be expressed as:

[0112]

[0113] where N0 is the state risk level of all single indicators, <s>refers to a measured indicator value of a single indicator quantity S, such as, for example, <s1>is a measured index value of the single index s1.

[0114] In a possible implementation, for each single index, a measured index value of the single index can be determined within which state risk level range the measured index value of the single index is in the classical domain range of the single index, and a first correlation degree of the single index with each state risk level can be determined in combination with a position of the measured index value of the single index in the classical domain range of the single index and a position in the section domain range, and a state risk level with the highest first correlation degree is taken as the state risk level of the single index.

[0115] In a possible implementation, the state risk levels of each functional module and the state risk level of the electric special vehicle can be determined according to the first correlation degrees of each single index with each state risk level. For example, for multiple single indexes in each functional module, a state risk level with the highest first correlation degree can be taken as the state risk level of the single index, and the state risk level of the functional module can be determined according to the state risk levels of the multiple single indexes in the functional module and the importance of the multiple single indexes in the functional module to the functional module. Then, the state risk level of the electric special vehicle can be determined according to the state risk levels of each functional module and the importance of each functional module to the electric special vehicle.

[0116] The embodiment proposes a multi-level evaluation system, which integrates the operation state evaluation of single indexes, functional modules, and electric special vehicles, and realizes multi-granularity state monitoring and evaluation from fine to coarse. Meanwhile, the embodiment fully utilizes the matter-element extension model, combines the operation state evaluation at each level, uses the correlation degree of the matter-element extension model to represent the state risk level of the single index, and then determines the state risk levels of each functional module and the electric special vehicle based on the first correlation degrees of the single indexes with each state risk level. The embodiment simplifies the operation state evaluation steps at each level, can be conveniently deployed in the corresponding Internet of Things terminal of the electric special vehicle, improves the intelligent operation and maintenance capability of the electric special vehicle, realizes comprehensive, real-time, and accurate monitoring of the vehicle operation state, and realizes fault early warning, in-process monitoring, and post-mortem based on the state risk levels at each level.

[0117] In a possible implementation, the determination of the state risk levels of the functional modules and the state risk level of the electric special vehicle based on the first correlation degrees of each single index with each state risk level includes:

[0118] For each functional module, a second correlation degree of the functional module with each state risk level is determined based on the first correlation degrees of multiple single indexes corresponding to the functional module with each state risk level.

[0119] Using the state risk level with the second highest correlation as the state risk level of the functional module;

[0120] Determining a third degree of association between the electric special vehicle and each state risk level based on the second degree of association between each functional module and each state risk level;

[0121] The state risk level with the third highest correlation degree is used as the state risk level of the electric special vehicle.

[0122] In this embodiment, for each functional module, a weighted calculation can be performed on the first correlation between the multiple single indicators corresponding to the functional module and the corresponding state risk level based on the importance of the multiple single indicators corresponding to the functional module to the functional module to obtain a second correlation between the functional module and the corresponding state risk level; the state risk level with the highest second correlation is used as the state risk level of the functional module, and then, based on the importance of the multiple functional modules corresponding to the electric special vehicle to the electric special vehicle, a weighted calculation is performed on the second correlation between the multiple functional modules corresponding to the electric special vehicle and the corresponding state risk level to obtain a third correlation between the electric special vehicle and the corresponding state risk level; the state risk level with the highest third correlation is used as the state risk level of the electric special vehicle.

[0123] In a possible implementation, calculating the first correlation between the single indicator and each state risk level based on the single indicator in the preset classical domain and section domain of the state risk level and the measured indicator value of the single indicator includes:

[0124] Calculate the i-th single indicator s according to the following formula i The first correlation degree with the k-th level of state risk

[0125]

[0126] in, and Each single indicator is s i The lower and upper thresholds of the classic domain of the k-th state risk level, a i and b i Each single indicator is s i The lower and upper thresholds of the section domain, i > for the single indicator s i The measured index value.

[0127] ​In this embodiment, it is assumed that there are three levels of preset state risk levels: k = 1, 2, 3 correspond to the three levels of state risk levels, where k = 1 refers to "abnormal", k = 2 refers to "warning", and k = 3 refers to "normal", then the i-th single indicator s i The status risk level is The corresponding k value.

[0128] In a possible implementation, determining the second correlation between the functional module and each state risk level based on the first correlation between the multiple single indicators corresponding to the functional module and each state risk level includes:

[0129] Using a hierarchical analysis method, obtaining a first judgment matrix corresponding to the functional module, and calculating a basic weight of each single indicator in the functional module based on the first judgment matrix, wherein the first judgment matrix is ​​used to represent the importance between multiple single indicators in the functional module;

[0130] The basic weights are modified using a variable weight comprehensive model based on factor space theory to obtain a variable weight vector for each single indicator in the functional module;

[0131] Based on the variable weight vector and the first correlation degrees between the plurality of single indicators corresponding to the functional modules and the risk levels of the respective states, a second correlation degree between the functional modules and the risk levels of the respective states is calculated.

[0132] In this embodiment, it is assumed that the electric special vehicle has a total of M2 functional modules, and the jth functional module has A single indicator j=1,...,M2, the basic weight of the jth functional module can be constructed through expert knowledge and hierarchical analysis method.

[0133] In this embodiment, a first judgment matrix of a single indicator relative to a functional module is constructed and recorded as The first judgment matrix is used to represent comparison values of the importance degrees of the single indexes in the function module relative to the function module. Diagonal elements of the first judgment matrix are all 1, and other elements are importance degrees of one single index relative to another single index for the function module. The more important, the greater the value. The AHP (analytic hierarchy process) method can be used to calculate the basic weight of the single index. For example, in order to ensure the consistency of the judgment matrix, consistency check can be performed. If the consistency check passes, normalization processing is performed on each column of the first judgment matrix, that is, each element of each column is divided by the sum of the column. In this way, a new matrix can be obtained, in which the sum of each column is 1. Then, an average value of each row of the normalized matrix is obtained, and a vector is obtained, which is the basic weight of each single index. If the consistency check does not pass, the first judgment matrix is adjusted again, and then the basic weight of each single index is calculated after the consistency check passes.

[0134] In this embodiment, in order to realize the fault duration early warning, the basic weight can be corrected by using a variable weight comprehensive model based on the factor space theory. The variable weight comprehensive model based on the factor space theory is a decision analysis method, which determines the weight of each factor by considering the importance and state balance degree of each factor in the decision. In this embodiment, each factor is each single index. The importance and state balance degree of each single index in the function module can be considered to correct the basic weight of each single index, and a variable weight vector of each single index is determined.

[0135] In this embodiment, based on the variable weight vector, the first correlation degree of the single indexes corresponding to the function module and the corresponding state risk level can be weighted and calculated to obtain the second correlation degree of the function module and each state risk level.

[0136] In a possible implementation, the basic weight is corrected by using the variable weight comprehensive model based on the factor space theory to obtain the variable weight vector, including:

[0137] The variable weight vector of the jth function module is calculated according to the following formula:

[0138] wherein, is the total number of single indexes in the jth function module, is the basic weight of the ith single index in the jth function module, i j is the ith single index in the jth function module, i j ​​The measured index value, α is the preset value, a i j and b i j are the i-th single indicator s in the j-th functional module i j The upper and lower thresholds of the section domain.

[0139] In a possible implementation, calculating the second correlation between the functional module and each state risk level based on the variable weight vector and the first correlation between the plurality of single indicators corresponding to the functional module and each state risk level includes:

[0140] The second correlation between the jth functional module and the kth level of state risk is calculated according to the following formula:

[0141]

[0142] Among them, the is the i-th single indicator s in the j-th functional module i j The first correlation degree with the k-th state risk level has been calculated previously.

[0143] In this embodiment, it is assumed that there are three levels of preset status risk levels: k = 1, 2, and 3 correspond to the three levels of status risk levels, where k = 1 refers to "abnormal", k = 2 refers to "warning", and k = 3 refers to "normal". The status risk level of the jth functional module is The corresponding k value.

[0144] In a possible implementation, determining the third degree of association between the electric special vehicle and each state risk level based on the second degree of association between each functional module and each state risk level includes:

[0145] A hierarchical analysis method is used to obtain a second judgment matrix corresponding to the electric special vehicle, and a basic weight of each functional module in the electric special vehicle is calculated based on the second judgment matrix, wherein the second judgment matrix is ​​used to represent the importance between multiple functional modules in the electric special vehicle;

[0146] Based on the basic weight of each functional module in the electric special vehicle and the second correlation between each functional module in the electric special vehicle and each state risk level, the third correlation between the electric special vehicle and each state risk level is calculated.

[0147] In this embodiment, it is assumed that the electric special vehicle has a total of M2 functional modules, and the basic weights of the M2 functions are constructed through expert knowledge and hierarchical analysis method.

[0148] In this embodiment, a second judgment matrix of M2 functional modules relative to the electric special vehicle is first constructed The second judgment matrix is used to represent the comparison value of the importance of the M2 functional modules in the electric special vehicle relative to the electric special vehicle. The diagonal elements of the second judgment matrix are all 1, and the remaining elements are the importance of one functional module relative to another functional module relative to the electric special vehicle. The more important, the greater the value. The basic weight of the functional module can be calculated by using the analytic hierarchy process. The specific calculation process can refer to the calculation of the basic weight of the single index described above, and will not be repeated here.

[0149] In this embodiment, based on the basic weight of each functional module in the electric special vehicle, the second correlation degree of each functional module in the electric special vehicle and the corresponding state risk level can be weighted and calculated to obtain the third correlation degree of the functional module and the corresponding state risk level.

[0150] In a possible implementation, the third correlation degree of the electric special vehicle and each state risk level is calculated based on the basic weight of each functional module in the electric special vehicle and the second correlation degree of each functional module in the electric special vehicle and each state risk level, comprising:

[0151] The third correlation degree Rk of the electric special vehicle and the kth state risk level is calculated according to the following formula k :

[0152]

[0153] Wherein, M2 is the total number of functional modules in the electric special vehicle, w 0,j is the basic weight of the M2 functional modules in the electric special vehicle, is the second correlation degree of the jth functional module and the kth state risk level.

[0154] In this embodiment, it is assumed that the preset state risk level has three levels: k = 1, 2, 3 correspond to three state risk levels, wherein k = 1 means "abnormal", k = 2 means "warning", and k = 3 means "normal". The state risk level of the electric special vehicle is the k value corresponding to max(R1, R2, R3).

[0155] In a possible implementation, the method further comprises:

[0156] When the state risk level of the electric special vehicle is a risk level requiring operation and maintenance work, the state risk levels of the single indicators are input into a pre-trained identification model, the identification model is executed, and an operation and maintenance work type output by the identification model is obtained, the operation and maintenance work type including side operation and maintenance, cloud side operation and maintenance, and cloud side and side collaborative operation and maintenance;

[0157] When the operation and maintenance work type is side operation and maintenance, first reminding information is output, the first reminding information being used to remind side personnel to perform operation and maintenance work;

[0158] When the operation and maintenance work type is cloud side operation and maintenance, the state risk levels of the single indicators, the state risk levels of the functional modules, and the state risk level of the electric special vehicle are sent to the cloud;

[0159] When the operation and maintenance work type is cloud side and side collaborative operation and maintenance, second reminding information is output to remind side personnel to perform operation and maintenance work, and the state risk levels of the single indicators, the state risk levels of the functional modules, and the state risk level of the electric special vehicle are sent to the cloud.

[0160] In this embodiment, when the state risk level of the electric special vehicle is "abnormal" or "pre-warning", it is a risk level requiring operation and maintenance work. At this time, a side operation and maintenance work shunting strategy can be executed to determine the responsible party for performing operation and maintenance work under the current state of the electric special vehicle. The state risk levels of the single indicators of the electric special vehicle can be input into a pre-trained identification model. For example, the state risk levels of the single indicators can be binary coded: "abnormal" is "00", "pre-warning" is "01", and "normal" is "10". The input of the pre-trained identification model is the state code of all single indicators, and the output codes "100" correspond to side operation and maintenance, the output code "010" corresponds to cloud side operation and maintenance, and the output code "001" corresponds to cloud side and side collaborative operation and maintenance. It should be noted that the identification model can be a neural network model, which can be obtained by training samples. The training samples can be the state risk levels of the single indicators of the electric special vehicle in a historical time period and the actual operation and maintenance work type.

[0161] In this embodiment, side operation and maintenance refers to operation and maintenance work that can be completed by side personnel such as a driver and a vehicle following worker. Cloud side operation and maintenance refers to operation and maintenance work that cannot be completed by side personnel and requires cloud dispatch of professional operation and maintenance personnel for repair. Cloud side and side collaborative operation and maintenance refers to operation and maintenance work that can be completed by side personnel through limited operation and maintenance capability to maintain a short running state of the vehicle, but requires cloud dispatch of professional operation and maintenance personnel for complete repair.

[0162] In the embodiment, when the operation and maintenance type identified by the identification model is side operation and maintenance, the first reminding information is directly output, and the first reminding information is used to remind the side personnel to perform operation and maintenance work; when the operation and maintenance type identified by the identification model is cloud operation and maintenance, the state risk levels of each single index of the electric special vehicle, the state risk levels of each functional module, and the state risk level of the electric special vehicle are sent to the cloud, and professional maintenance personnel are allocated by the cloud according to the state risk levels; when the operation and maintenance type identified by the identification model is cloud-side collaborative operation and maintenance, the second reminding information is immediately output, the side personnel is reminded to perform vehicle maintenance, keep the vehicle in normal operation, keep the vehicle in a short running state, and the state risk levels of each single index of the electric special vehicle, the state risk levels of each functional module, and the state risk level of the electric special vehicle are sent to the cloud, and professional maintenance personnel are allocated by the cloud to completely maintain the vehicle according to the state risk levels.

[0163] The Internet of Things terminal at the edge in the embodiment has edge computing capability and an AI module, and can realize intelligent analysis of the terminal on site. In order to enhance the data analysis capability at the edge, reduce the demand for communication resources at the edge, and reduce the computing pressure of the cloud, the embodiment can perform an edge operation and maintenance work distribution strategy by the Internet of Things terminal at the edge, to realize fast response to faults and accurate allocation of operation and maintenance work.

[0164] Figure 3 A structure block diagram of an operation state processing device of an electric special vehicle provided by an embodiment of the present disclosure is shown, and the device can be realized as part or all of an electronic device by software, hardware, or a combination of both. As shown in Figure 3 The operation state processing device of the electric special vehicle includes:

[0165] The first acquisition module 301 is configured to acquire the classical domain and the section domain of a preset state risk level of each single index of an electric special vehicle. The electric special vehicle corresponds to a plurality of functional modules, and each functional module corresponds to a plurality of single indexes.

[0166] The second acquisition module 302 is configured to acquire a measured index value of each single index.

[0167] The calculation module 303 is configured to calculate, for each single index, a first correlation degree between the single index and each state risk level according to the classical domain and the section domain of a preset state risk level of the single index and the measured index value of the single index.

[0168] The first level determination module 304 is configured to determine the state risk level with the highest first correlation degree as the state risk level of the single index.

[0169] The second level determination module 305 is configured to determine the state risk level of each functional module and the state risk level of the electric special vehicle based on the first correlation between each single indicator and each state risk level.

[0170] In a possible implementation, the second level determination module is configured to:

[0171] For each functional module, determining a second correlation between the functional module and each state risk level based on a first correlation between a plurality of single indicators corresponding to the functional module and each state risk level;

[0172] Using the state risk level with the second highest correlation as the state risk level of the functional module;

[0173] Determining a third degree of association between the electric special vehicle and each state risk level based on the second degree of association between each functional module and each state risk level;

[0174] The state risk level with the third highest correlation degree is used as the state risk level of the electric special vehicle.

[0175] In a possible implementation, the calculation module is configured to:

[0176] Calculate the i-th single indicator s according to the following formula i The first correlation degree with the k-th level of state risk

[0177]

[0178] in, and They are single indicators s i The lower and upper thresholds of the classic domain of the k-th state risk level, a i and b i They are single indicators s i The lower and upper thresholds of the section domain, i > for the single indicator s i The measured index value.

[0179] In a possible implementation, the portion of the second level determination module that determines the second degree of association between the functional module and each state risk level based on the first degree of association between the multiple single indicators corresponding to the functional module and each state risk level is configured as follows:

[0180] ​Using a hierarchical analysis method, a first judgment matrix corresponding to the functional module is obtained, and a basic weight of each single indicator in the functional module is calculated based on the first judgment matrix, wherein the first judgment matrix is ​​used to represent a comparison value of the importance between multiple single indicators in the functional module;

[0181] The basic weights of the single indicators are modified by using a variable weight comprehensive model based on factor space theory to obtain the variable weight vectors of the single indicators in the functional module;

[0182] Based on the variable weight vector and the first correlation degrees between the plurality of single indicators corresponding to the functional modules and the risk levels of the respective states, a second correlation degree between the functional modules and the risk levels of the respective states is calculated.

[0183] In one possible implementation, the second level determination module uses a variable weight comprehensive model based on factor space theory to modify the basic weights of the single indicators, and the part that obtains the variable weight vector of each single indicator in the functional module is configured as follows:

[0184] According to the following formula, the number of the jth functional module is calculated The variable weight vector of a single indicator

[0185] in, is the total number of single indicators in the jth functional module, For the jth functional module The basic weight of a single indicator, i j > is the i-th single indicator s in the j-th functional module i j The measured index value, α is the preset value, a i j and b i j are the i-th single indicator s in the j-th functional module i j The upper and lower thresholds of the section domain.

[0186] In one possible implementation, the portion of the second level determination module that calculates the second degree of association between the functional module and each state risk level based on the variable weight vector and the first degrees of association between the multiple single indicators corresponding to the functional module and each state risk level is configured as follows:

[0187] The second correlation between the jth functional module and the kth level of state risk level is calculated according to the following formula:

[0188] ​

[0189] wherein, is the i-th single indicator s in the j-th functional module i j is the first association degree of the k-th state risk level.

[0190] In a possible implementation, the part of the second level determination module that determines the third association degree of the electric special vehicle and each state risk level based on the second association degree of each functional module and each state risk level is configured to:

[0191] obtain a second judgment matrix corresponding to the electric special vehicle by using the analytic hierarchy process, and calculate the basic weight of each functional module in the electric special vehicle based on the second judgment matrix, wherein the second judgment matrix is used to represent the comparison value of the importance between the multiple functional modules in the electric special vehicle;

[0192] calculate the third association degree of the electric special vehicle and each state risk level based on the basic weight of each functional module in the electric special vehicle and the second association degree of each functional module in the electric special vehicle and each state risk level.

[0193] In a possible implementation, the part of the second level determination module that determines the third association degree of the electric special vehicle and each state risk level based on the basic weight of each functional module in the electric special vehicle and the second association degree of each functional module in the electric special vehicle and each state risk level is configured to:

[0194] calculate the third association degree R of the electric special vehicle and the k-th state risk level according to the following formula: k

[0195]

[0196] wherein M2 is the total number of functional modules in the electric special vehicle, w 0,j is the basic weight of the j-th functional module in the electric special vehicle, is the second association degree of the j-th functional module and the k-th state risk level.

[0197] In a possible implementation, the apparatus further includes:

[0198] ​The type identification module is configured to input the state risk level of each single index into a pre-trained identification model when the state risk level of the electric special vehicle is a risk level requiring operation and maintenance work, execute the identification model, and obtain an operation and maintenance work type output by the identification model, the operation and maintenance work type including side operation and maintenance, cloud side operation and maintenance, and cloud side and edge collaborative operation and maintenance.

[0199] The output module is configured to output first reminding information when the operation and maintenance work type is side operation and maintenance, the first reminding information being used to remind side personnel to perform operation and maintenance work; send the state risk level of each single index of the electric special vehicle, the state risk level of each functional module, and the state risk level of the electric special vehicle to the cloud when the operation and maintenance work type is cloud side operation and maintenance; and output second reminding information to remind side personnel to perform operation and maintenance work and send the state risk level of each single index of the electric special vehicle, the state risk level of each functional module, and the state risk level of the electric special vehicle to the cloud when the operation and maintenance work type is cloud side and edge collaborative operation and maintenance.

[0200] The technical terms and technical features mentioned in the device embodiments are the same as or similar to those mentioned in the above method embodiments, and the explanation and description of the technical terms and technical features involved in the device can refer to the explanation and description of the above method embodiments, which will not be repeated here.

[0201] The present disclosure also discloses an electronic device, Figure 4 A structural block diagram of an electronic device according to an embodiment of the present disclosure is shown.

[0202] As Figure 4 shown, the electronic device 400 includes a memory 401 and a processor 402, wherein the memory 401 is used to store one or more computer instructions, and the one or more computer instructions are executed by the processor 402 to implement the method according to the embodiment of the present disclosure.

[0203] Figure 5 A structural schematic diagram of a computer system suitable for implementing the method of the embodiment of the present disclosure is shown.

[0204] As Figure 5 shown, the computer system 500 includes a processing unit 501, which can perform various processes in the above embodiments according to programs stored in a read-only memory (ROM) 502 or programs loaded from a storage portion 508 to a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the computer system 500 are also stored. The processing unit 501, the ROM 502, and the RAM 503 are connected to each other through a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0205] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a display device such as a cathode ray tube (CRT), a liquid crystal display (LCD), etc., and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as necessary. A removable recording medium 511 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc. is attached to the drive 510 as necessary, so that a computer program read out from it is installed in the storage section 508 as necessary. Among them, the processing unit 501 can be implemented as a CPU, a GPU, a TPU, a FPGA, a NPU, etc.

[0206] In particular, according to embodiments of the present disclosure, the method described above can be implemented as a computer software program. For example, embodiments of the present disclosure include a computer program product comprising computer instructions which, when executed by a processor, implement the method steps described above. In such embodiments, the computer program product can be downloaded and installed from a network by the communication section 509, and / or installed from the removable recording medium 511.

[0207] The flow diagrams and the block diagrams in the drawings are illustrations of possible architectures, functions, and operations 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 function(s). 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 the blocks may

[0208] The units or modules described in the embodiments of the present disclosure can be implemented by means of software, or by means of programmable hardware. The described units or modules can also be provided in a processor, and the names of these units or modules do not constitute a limitation on the units or modules themselves in some cases.

[0209] As another aspect, the disclosure also provides a computer readable storage medium, which can be the computer readable storage medium contained in the electronic device or the computer system in the above embodiments; or can be a computer readable storage medium existing separately and not assembled into a device. The computer readable storage medium stores one or more programs used by one or more processors to execute the method described in the disclosure.

[0210] The above description is merely the preferred embodiments of the disclosure and the explanation of the applied technical principles. It should be understood by those skilled in the art that the inventive scope of the 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 the combinations of the above technical features or equivalent features without departing from the inventive concept. For example, the technical solutions formed by the mutual replacement of the above features and the technical features disclosed in the disclosure (but not limited to) having similar functions. < / s> ​

Claims

1. A method for processing the operating status of an electric special vehicle, characterized in that: include: Obtaining the classic domain and the section domain of each single indicator of the electric special vehicle in a preset state risk level, wherein the electric special vehicle corresponds to multiple functional modules, and each functional module corresponds to multiple single indicators; Get the measured indicator value of each single indicator; For each single indicator, calculate a first correlation between the single indicator and each state risk level according to the single indicator in the preset classical domain and section domain of the state risk level and the measured indicator value of the single indicator; Using the state risk level with the highest first correlation as the state risk level of the single indicator; Determining the state risk level of each functional module and the state risk level of the electric special vehicle based on the first correlation between each single indicator and each state risk level; The determining of the state risk level of each functional module and the state risk level of the electric special vehicle based on the first correlation between each single indicator and each state risk level includes: For each functional module, based on the importance of the multiple single indicators corresponding to the functional module to the functional module, a weighted calculation is performed on the first correlation between the multiple single indicators corresponding to the functional module and the corresponding state risk level to obtain a second correlation between the functional module and the corresponding state risk level; Using the state risk level with the second highest correlation as the state risk level of the functional module; Based on the importance of the multiple functional modules corresponding to the special electric vehicle to the special electric vehicle, a weighted calculation is performed on the second correlation between the multiple functional modules corresponding to the special electric vehicle and the corresponding state risk level to obtain a third correlation between the special electric vehicle and the corresponding state risk level; The state risk level with the third highest correlation degree is used as the state risk level of the electric special vehicle.

2. The method according to claim 1, characterized in that Calculating the first correlation between the single indicator and each state risk level according to the single indicator in the preset classical domain and section domain of the state risk level and the measured indicator value of the single indicator includes: Calculate the i-th single indicator s according to the following formula i The first correlation degree with the k-th level of state risk in, and Each single indicator is s i The lower and upper thresholds of the classic domain of the k-th state risk level, a i and b i Each single indicator is s i The lower and upper thresholds of the section domain, i > for the single indicator s i The measured index value.​ 3. The method according to claim 1, characterized in that The determining, based on the first correlations between the plurality of single indicators corresponding to the functional modules and the risk levels of the respective states, a second correlation between the functional modules and the risk levels of the respective states includes: Using a hierarchical analysis method, a first judgment matrix corresponding to the functional module is obtained, and a basic weight of each single indicator in the functional module is calculated based on the first judgment matrix, wherein the first judgment matrix is ​​used to represent a comparison value of the importance between multiple single indicators in the functional module; The basic weights of the single indicators are modified by using a variable weight comprehensive model based on factor space theory to obtain the variable weight vectors of the single indicators in the functional module; Based on the variable weight vector and the first correlation degrees between the plurality of single indicators corresponding to the functional modules and the risk levels of the respective states, a second correlation degree between the functional modules and the risk levels of the respective states is calculated.

4. The method according to claim 3, characterized in that The variable weight comprehensive model based on factor space theory is used to modify the basic weight of each single indicator to obtain the variable weight vector of each single indicator in the functional module, including: According to the following formula, the number of the jth functional module is calculated The variable weight vector of a single indicator in, is the total number of single indicators in the jth functional module, For the jth functional module The basic weight of a single indicator, i j > is the i-th single indicator s in the j-th functional module i j The measured index value, α is the preset value, a i j and b i j are the i-th single indicator s in the j-th functional module i j The upper and lower thresholds of the section domain.​ 5. The method according to claim 4, characterized in that The calculating, based on the variable weight vector and the first correlation between the plurality of single indicators corresponding to the functional module and the risk level of each state, the second correlation between the functional module and the risk level of each state includes: The second correlation between the jth functional module and the kth level of state risk level is calculated according to the following formula: in, is the i-th single indicator s in the j-th functional module i j The first degree of association with the k-th state risk level.

6. The method according to claim 1, characterized in that The determining of the third correlation between the electric special vehicle and each state risk level based on the second correlation between each functional module and each state risk level includes: Using a hierarchical analysis method, a second judgment matrix corresponding to the electric special vehicle is obtained, and based on the second judgment matrix, a basic weight of each functional module in the electric special vehicle is calculated, wherein the second judgment matrix is ​​used to represent a comparison value of the importance between multiple functional modules in the electric special vehicle; Based on the basic weight of each functional module in the electric special vehicle and the second correlation between each functional module in the electric special vehicle and each state risk level, the third correlation between the electric special vehicle and each state risk level is calculated.

7. The method according to claim 6, characterized in that The calculating, based on the basic weight of each functional module in the electric special vehicle and the second correlation between each functional module in the electric special vehicle and each state risk level, of the third correlation between the electric special vehicle and each state risk level includes: The third correlation R between the electric special vehicle and the k-th level state risk level is calculated according to the following formula: k : Wherein, M2 is the total number of functional modules in the electric special vehicle, w 0,j is the basic weight of the jth functional module in the electric special vehicle, is the second correlation degree between the j-th functional module and the k-th state risk level.

8. The method according to claim 1, characterized in that The method further comprises: When the state risk level of the electric special vehicle is a risk level requiring operation and maintenance work, the state risk level of each single indicator is input into a pre-trained recognition model, and the recognition model is executed to obtain the operation and maintenance work type output by the recognition model, and the operation and maintenance work type includes edge-side operation and maintenance, cloud-side operation and maintenance, and cloud-edge collaborative operation and maintenance; When the operation and maintenance work type is side operation and maintenance, outputting a first reminder message, wherein the first reminder message is used to remind side personnel to perform the operation and maintenance work; When the operation and maintenance work type is cloud-side operation and maintenance, the status risk level of each single indicator of the electric special vehicle, the status risk level of each functional module, and the status risk level of the electric special vehicle are sent to the cloud; When the operation and maintenance work type is cloud-edge collaborative operation and maintenance, a second reminder message is output to remind the side personnel to perform operation and maintenance work and send the status risk level of each single indicator of the electric special vehicle, the status risk level of each functional module and the status risk level of the electric special vehicle to the cloud.

9. A running status processing device for electric special vehicles, characterized in that: include: A first acquisition module is configured to obtain a classic domain and a section domain of a preset state risk level for each single indicator of an electric special vehicle, wherein the electric special vehicle corresponds to a plurality of functional modules, and each functional module corresponds to a plurality of single indicators; A second acquisition module is configured to obtain the measured indicator value of each single indicator; a calculation module configured to calculate, for each single indicator, a first correlation between the single indicator and each state risk level based on the single indicator in a preset classical domain and a section domain of the state risk level and a measured indicator value of the single indicator; A first level determination module is configured to use the state risk level with the highest first correlation as the state risk level of the single indicator; A second level determination module is configured to determine the state risk level of each functional module and the state risk level of the electric special vehicle based on the first correlation between each single indicator and each state risk level; The second level determination module is configured to: For each functional module, based on the importance of the multiple single indicators corresponding to the functional module to the functional module, a weighted calculation is performed on the first correlation between the multiple single indicators corresponding to the functional module and the corresponding state risk level to obtain a second correlation between the functional module and the corresponding state risk level; Using the state risk level with the second highest correlation as the state risk level of the functional module; Based on the importance of the multiple functional modules corresponding to the special electric vehicle to the special electric vehicle, a weighted calculation is performed on the second correlation between the multiple functional modules corresponding to the special electric vehicle and the corresponding state risk level to obtain a third correlation between the special electric vehicle and the corresponding state risk level; The state risk level with the third highest correlation degree is used as the state risk level of the electric special vehicle.

10. The device according to claim 9, characterized in that The computing module is configured to: Calculate the i-th single indicator s according to the following formula i The first correlation degree with the k-th level of state risk in, and Each single indicator is s i The lower and upper thresholds of the classic domain of the k-th state risk level, a i and b i Each single indicator is s i The lower and upper thresholds of the section domain, i > for the single indicator s i The measured index value.​ 11. The device according to claim 9, characterized in that The part of the second level determination module that determines the second correlation between the functional module and each state risk level based on the first correlation between the multiple single indicators corresponding to the functional module and each state risk level is configured as follows: Using a hierarchical analysis method, a first judgment matrix corresponding to the functional module is obtained, and a basic weight of each single indicator in the functional module is calculated based on the first judgment matrix, wherein the first judgment matrix is ​​used to represent a comparison value of the importance between multiple single indicators in the functional module; The basic weights of the single indicators are modified by using a variable weight comprehensive model based on factor space theory to obtain the variable weight vectors of the single indicators in the functional module; Based on the variable weight vector and the first correlation degrees between the plurality of single indicators corresponding to the functional modules and the risk levels of the respective states, a second correlation degree between the functional modules and the risk levels of the respective states is calculated.

12. The device according to claim 11, characterized in that The second level determination module adopts a variable weight comprehensive model based on factor space theory to modify the basic weight of each single indicator, and the part of obtaining the variable weight vector of each single indicator in the functional module is configured as follows: According to the following formula, the number of the jth functional module is calculated The variable weight vector of a single indicator in, is the total number of single indicators in the jth functional module, For the jth functional module The basic weight of a single indicator, i j > is the i-th single indicator s in the j-th functional module i j The measured index value, α is the preset value, a i j and b i j are the i-th single indicator s in the j-th functional module i j The upper and lower thresholds of the section domain.​ 13. The device according to claim 12, characterized in that The part of the second level determination module that calculates the second correlation degree between the functional module and each state risk level based on the variable weight vector and the first correlation degrees between the multiple single indicators corresponding to the functional module and each state risk level is configured as follows: The second correlation between the jth functional module and the kth level of state risk level is calculated according to the following formula: in, is the i-th single indicator s in the j-th functional module i j The first degree of association with the k-th state risk level.

14. The device according to claim 9, characterized in that The part of the second level determination module that determines the third degree of association between the electric special vehicle and each state risk level based on the second degree of association between each functional module and each state risk level is configured as follows: Using a hierarchical analysis method, a second judgment matrix corresponding to the electric special vehicle is obtained, and based on the second judgment matrix, a basic weight of each functional module in the electric special vehicle is calculated, wherein the second judgment matrix is ​​used to represent a comparison value of the importance between multiple functional modules in the electric special vehicle; Based on the basic weight of each functional module in the electric special vehicle and the second correlation between each functional module in the electric special vehicle and each state risk level, the third correlation between the electric special vehicle and each state risk level is calculated.

15. The device according to claim 14, characterized in that The portion of the second level determination module that calculates the third degree of association between the electric special vehicle and each state risk level based on the basic weight of each functional module in the electric special vehicle and the second degree of association between each functional module in the electric special vehicle and each state risk level is configured as follows: The third correlation R between the electric special vehicle and the k-th level state risk level is calculated according to the following formula: k : Wherein, M2 is the total number of functional modules in the electric special vehicle, w 0,j is the basic weight of the jth functional module in the electric special vehicle, is the second correlation degree between the j-th functional module and the k-th state risk level.

16. The device according to claim 9, characterized in that The device further comprises: a type identification module configured to input the status risk level of each single indicator into a pre-trained identification model when the status risk level of the electric special vehicle is a risk level requiring operation and maintenance work, execute the identification model, and obtain the operation and maintenance work type output by the identification model, where the operation and maintenance work type includes edge-side operation and maintenance, cloud-side operation and maintenance, and cloud-edge collaborative operation and maintenance; The output module is configured to output a first reminder message when the operation and maintenance work type is edge operation and maintenance, and the first reminder message is used to remind edge personnel to perform operation and maintenance work; when the operation and maintenance work type is cloud-side operation and maintenance, the status risk level of each single indicator of the special electric vehicle, the status risk level of each functional module, and the status risk level of the special electric vehicle are sent to the cloud; when the operation and maintenance work type is cloud-edge collaborative operation and maintenance, the second reminder message is output to remind edge personnel to perform operation and maintenance work and send the status risk level of each single indicator of the special electric vehicle, the status risk level of each functional module, and the status risk level of the special electric vehicle to the cloud.

17. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory is used to store one or more computer instructions, wherein the one or more computer instructions are executed by the processor to implement the method according to any one of claims 1 to 8.

18. A readable storage medium, characterized in that Computer instructions are stored thereon, and when the computer instructions are executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images