A method and system for optimizing the distribution of extended-range power sources for welding engineering vehicles

Abstract

The present invention relates to the field of data processing technology, and in particular to a method and system for optimizing the allocation of extended-range power sources for welding engineering vehicles. The method includes the steps of: sorting the power demand values ​​appearing in the vehicle power demand time series from large to small to obtain a power demand interval, and recording each power demand value in the power demand interval as a unit power; obtaining the left change weight and the right change weight of the unit power through the data changes on the left and right sides of each position of the unit power in the power demand time series; calculating the importance of the unit power; obtaining the prominence of the unit power through the deviation between the importance of the unit power and the importance of the adjacent unit power in the power demand interval; dividing the power demand interval according to the prominence of each unit power to assist in the allocation of the extended-range power source for welding engineering vehicles, and effectively improving the accuracy of the power source allocation.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a method and system for optimizing the distribution of an extended-range power source for a welding engineering vehicle. Background Art

[0002] The welding engineering vehicle adopts an extended-range power source, which combines the advantages of traditional fuel engines and electric motors. During the operation of the welding engineering vehicle, it can flexibly adjust the working status of the internal combustion engine and the electric motor according to the actual power requirements of the welding engineering vehicle, thereby maximizing the utilization of energy and providing a more efficient and environmentally friendly power solution for the welding engineering vehicle.

[0003] Welding engineering vehicles often face complex and changeable working conditions in actual operations, with large load changes, making it difficult to obtain more accurate power requirements. In the prior art, research on vehicle power requirements tends to focus on how to manage battery power to achieve the purpose of reasonable distribution of power sources. For example, the patent application document with publication number CN112926211A discloses a fuel cell vehicle energy management optimization method based on working condition prediction. This method uses a Markov model to predict driving conditions for hybrid fuel cell vehicles, in which the motor's required power interval is divided into several state intervals by unit power, and the predicted power is obtained based on the power characteristics of the state interval, thereby obtaining the motor's required power, and finally combining the inner layer control and the outer layer control to achieve energy distribution of multiple power sources.

[0004] The existing technology can optimize the working point of the power source to a certain extent and extend the battery life, but it does not take into account the actual change state of power when dividing the state interval. Directly using a fixed power interval cannot accurately obtain the actual power demand of the vehicle, affecting the accuracy of power source allocation.

[0005] Based on this, how to accurately obtain the required power of the vehicle so as to achieve reasonable allocation of power sources is an urgent problem to be solved by those skilled in the art. Summary of the invention

[0006] In order to solve the technical problem of how to accurately obtain the required power of a vehicle and thus realize reasonable distribution of power sources, the present invention provides a method and system for optimizing distribution of extended-range power sources for welding engineering vehicles.

[0007] In a first aspect, the present invention provides a method for optimizing the distribution of a range-extended power source for a welding engineering vehicle, which adopts the following technical solution:

[0008] A method for optimizing the distribution of extended-range power sources for welding engineering vehicles, comprising the steps of:

[0009] The power demand values ​​appearing in the vehicle power demand time series are sorted from large to small to obtain a power demand interval, and each power demand value in the power demand interval is recorded as a unit power; the left change weight and the right change weight of the unit power are obtained by the data changes on the left and right sides of each position in the power demand time series; the importance of the unit power is calculated: ; In the formula, represents the importance of the i-th unit power, It represents the total number of types of adjacent unit powers on the left and right sides of the i-th unit power in the power demand time series. Indicates the total number of types corresponding to the unit power with the highest number of occurrences in the power demand time series. , They represent the left and right change weights of the i-th unit power, respectively. , They represent the number of adjacent unit powers on the left and right of the i-th unit power in the power demand timing sequence, Represents the total number of types of unit power; obtains the prominence of the unit power through the degree of deviation between the importance of the unit power and the importance of adjacent unit powers in the power demand interval; divides the power demand interval according to the prominence of each unit power to assist in the allocation of extended-range power sources for welding engineering vehicles.

[0010] The present invention predicts the power demand of a welding engineering vehicle through a hidden Markov model, thereby realizing accurate allocation of power sources. In the process, the present invention takes into account that when the power demand interval is divided into state intervals, the fixed-size state intervals do not take into account the changes in each unit power, resulting in a low accuracy of the power demand prediction result. Based on this, the present invention obtains the data changes on the left and right sides of each position of the unit power in the vehicle power demand time series sequence to accurately obtain the importance of the unit power, thereby effectively improving the accuracy of the state interval division; on this basis, the present invention also takes into account that when the state interval division is directly based on the importance, the state interval division accuracy corresponding to some unit powers is low. Based on this, the present invention further obtains the prominence of the importance of each unit power, and realizes accurate division of the state interval according to the prominence of the importance, thereby effectively improving the accuracy of the power demand prediction of the welding engineering vehicle, thereby effectively improving the accuracy of the power source allocation.

[0011] According to a method for optimizing the distribution of extended-range power sources for welding engineering vehicles provided by the present invention, the power demand values ​​appearing in the vehicle power demand time series sequence are sorted from large to small, and the method also includes: collecting the power required during the operation of the welding engineering vehicle, and arranging the power demand value collected at each moment as a data point in time series to obtain a power demand time series sequence.

[0012] According to a method for optimizing the distribution of extended-range power sources for welding engineering vehicles provided by the present invention, the left-side change weight and the right-side change weight of the unit power are obtained, including: calculating the importance of the left side of the unit power ; In the formula, represents the mean value of the power variance of the data points on the left side of the i-th unit power in the power demand time series, represents the mean value of the power variance of the data points on the right side of the i-th unit power in the power demand time series, represents the power demand value of the i-th unit power, It represents the mean of the power means of the data points on the left side of the i-th unit power in the power demand time series. It obtains the sum of the importance of the left and right sides of the unit power, and takes the ratio of the left importance to the sum as the left change weight, and takes the ratio of the right importance to the sum as the right change weight.

[0013] The present invention provides an accurate importance calculation formula for the left-side change weight and the right-side change weight of unit power. By analyzing the power characteristics on the left and right sides of the unit power, the left-side change weight and the right-side change weight can be accurately obtained, so that the importance of the unit power can be accurately obtained based on this.

[0014] According to a method for optimizing the distribution of extended-range power sources for welding engineering vehicles provided by the present invention, the prominence of the unit power satisfies the relationship:

[0015] ;

[0016] In the formula, represents the prominence of the i-th unit power, , , Respectively represent the i-th and , The importance of a unit of power, represents the mean importance of all unit powers, Represents the absolute value symbol.

[0017] The present invention provides an accurate calculation formula for the prominence of unit power. By analyzing the deviation degree of importance between the unit power and the unit powers adjacent to it on the left and right, the prominence of the unit power can be accurately obtained.

[0018] According to a method for optimizing the distribution of extended-range power sources for welding engineering vehicles provided by the present invention, the power demand interval is divided according to the prominence of each unit power, including: dividing the power demand interval into multiple initial state intervals according to each unit power, one unit power corresponds to one initial state interval; presetting a fusion threshold; taking the initial state interval corresponding to the unit power whose prominence is less than the fusion threshold as the state interval to be fused, obtaining the minimum prominence corresponding to the adjacent initial state intervals on the left and right sides of the state interval to be fused in the power demand interval, merging the state interval to be fused with the initial state interval corresponding to the minimum prominence to obtain a state interval, and finally dividing the power demand interval into multiple state intervals.

[0019] The present invention can effectively improve the accuracy of state interval division by fusing initial state intervals with less prominence, so that the power prediction value of the welding engineering vehicle can be accurately obtained based on this.

[0020] According to a method for optimizing the allocation of an extended-range power source for a welding engineering vehicle provided by the present invention, the power demand interval is divided according to the prominence of each unit power to assist in the allocation of the extended-range power source for the welding engineering vehicle, including: processing the state interval of the power demand of the vehicle at the current moment through a hidden Markov model to obtain the state interval of the vehicle's power demand prediction value, using the power demand mean of the state interval as the vehicle's power demand prediction value, and allocating power to the welding engineering vehicle according to the power demand prediction value.

[0021] According to a method for optimizing distribution of extended-range power sources for welding engineering vehicles provided by the present invention, power is distributed to the welding engineering vehicle according to a power demand prediction value, and then the method further includes: abnormal monitoring of the power demand prediction value of the vehicle.

[0022] The present invention takes into account that the power demand prediction value of the welding engineering vehicle cannot exceed the safety range. Abnormal power demand may mean that the welding engineering vehicle is in poor working condition or has potential faults. Therefore, by performing abnormal monitoring on the power demand prediction value, the frequency of equipment failures can be effectively reduced.

[0023] In a second aspect, the present invention provides a range-extended power source distribution optimization system for a welding engineering vehicle, which adopts the following technical solution:

[0024] A range-extended power source distribution optimization system for a welding engineering vehicle comprises: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned range-extended power source distribution optimization method for a welding engineering vehicle is implemented.

[0025] By adopting the above technical solution, the above-mentioned extended-range power source distribution optimization method for a welding engineering vehicle is generated into a computer program and stored in a memory to be loaded and executed by a processor, so that a terminal device is made according to the memory and the processor for easy use.

[0026] The present invention has the following technical effects:

[0027] Based on the above technical scheme, when realizing the power source allocation of the welding engineering vehicle, the present invention predicts the power demand of the welding engineering vehicle through the hidden Markov model, so as to realize the accurate allocation of the power source. In this process, the present invention takes into account that when the power demand interval is divided into state intervals, the state intervals of fixed size will affect the accuracy of the power demand prediction results. Based on this, the present invention obtains the data changes on the left and right sides of each position of the unit power in the vehicle power demand time series sequence, accurately obtains the importance of the unit power, and effectively improves the accuracy of the state interval division; on this basis, the present invention also takes into account that when the state interval division is directly based on the importance, the state interval division accuracy corresponding to some unit powers is low. Based on this, the present invention further obtains the prominence of the importance of each unit power, and realizes the accurate division of the state interval according to the prominence of the importance, thereby effectively improving the accuracy of the power source allocation. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0029] Figure 1 A schematic flow chart of a method for optimizing the distribution of an extended-range power source for a welding engineering vehicle provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0030] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0031] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0032] It should be noted that in the prior art, the motor's required power interval is divided into several state intervals by unit power, and the predicted power is obtained based on the power characteristics of the state intervals, and finally the energy distribution of multiple power sources is realized by combining the inner layer control and the outer layer control. However, the actual change state of power is not considered when dividing the state intervals. The fixed-size power intervals directly divided by unit power cannot accurately obtain the actual power demand of the vehicle, thus affecting the accuracy of power source distribution.

[0033] Based on this, the embodiment of the present invention discloses a method for optimizing the distribution of extended-range power sources for welding engineering vehicles. The method obtains the importance of each unit power by analyzing the power data changes on both sides of each unit power in the data sequence, and divides the state interval according to the importance of the unit power, so that the power demand prediction value of the welding engineering vehicle can be accurately obtained based on this, and the power distribution can be realized. For details, please refer to Figure 1 As shown, Figure 1 A schematic flow chart of a method for optimizing the distribution of an extended-range power source for a welding engineering vehicle provided in an embodiment of the present invention, the method comprising the following steps S1 to S4.

[0034] S1: sort the power demand values ​​appearing in the vehicle power demand time series from large to small to obtain a power demand interval, and record each power demand value in the power demand interval as a unit power.

[0035] It should be noted that the power consumption of welding engineering vehicles during actual operation includes two parts: vehicle driving and welding process. The power requirements of the vehicle are different in different links and environments. Therefore, when allocating power to the vehicle, it is necessary to consider the frequency of occurrence of different power demand values, so as to divide the state interval more reasonably.

[0036] For example, in an embodiment of the present invention, the power demand values ​​appearing in the vehicle power demand time series sequence are sorted from large to small, and the process also includes: collecting the power required during the operation of the welding engineering vehicle, and taking the power demand value collected at each moment as a data point and arranging them in time series to obtain a power demand time series sequence.

[0037] The acquisition frequency and the acquisition period etc. can be set according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this.

[0038] After the power demand time series of the welding engineering vehicle is obtained based on the above steps, each power demand value appearing in the power demand time series can be obtained, and the power demand values ​​are sorted by size to obtain the power demand range for subsequent data processing.

[0039] S2: Obtain the left and right change weights of the unit power through the data changes on the left and right sides of each position in the power demand time series, and calculate the importance of the unit power.

[0040] It should be noted that the changes in the unit power on both sides of each position in the power demand time series can reflect the current change trend of the unit power. If the unit power shows a significant change trend on both sides, it means that the unit power may be at a critical node of the power demand change, and the corresponding importance is higher.

[0041] Based on this, the embodiment of the present invention can obtain the weights of the data on both sides of the unit power by respectively obtaining the power data on the left and right sides of the unit power to reflect the changing trend of the unit power at each position in the time series, and finally obtain the importance of each unit power.

[0042] By way of example, in an embodiment of the present invention, the left-side change weight and the right-side change weight of the unit power are obtained, including: calculating the importance of the left side of the unit power; obtaining the sum of the importance of the left and right sides of the unit power, and taking the ratio of the left-side importance to the sum as the left-side change weight, and taking the ratio of the right-side importance to the sum as the right-side change weight.

[0043] For example, the importance of determining the left side of the unit power can be specifically referred to the following relationship:

[0044] ;

[0045] In the formula, represents the importance of the left side of the i-th unit power, represents the mean value of the power variance of the data points on the left side of the i-th unit power in the power demand time series, represents the mean value of the power variance of the data points on the right side of the i-th unit power in the power demand time series, represents the power demand value of the i-th unit power, It represents the mean of the power mean of the data points on the left side of the i-th unit power in the power demand time series, Represents the absolute value symbol.

[0046] In the above formula, It indicates the relative size of the change on the left side of the i-th unit power. The larger the value is, the greater the change in the power demand of the welding engineering vehicle on the left side of the i-th unit power is, the more complex the trend is, the more difficult it is to predict subsequent data through the data on the left side of the unit power, and the higher the importance of the i-th unit power is.

[0047] It represents the relative gap between the data mean on the left side of the i-th unit power in the power demand time series and the power demand value of the i-th unit power. The larger the value is, the more prominent the i-th unit power is, the more difficult it is to predict, and the higher the corresponding importance is.

[0048] Take an example to illustrate how to obtain the mean of the power variance of the left and right data points of each unit power in the power demand time series sequence: the power demand time series sequence is {102, 104, 101, 102, 103, 101, 103, 104, 101}, then the power demand values ​​corresponding to the left data points of each position of the unit power 101 in the power demand time series sequence are 102 and 104, 102 and 103, 103 and 104, first obtain the variance of 102 and 104, the variance of 102 and 103, and the variance of 104. 3 and 104, and then obtain the mean of the variances as the mean of the power variances of the data points on the left side of each position of the unit power 101 in the power demand time series sequence; similarly, the power demand values ​​corresponding to the data points on the right side of each position of the unit power 101 in the power demand time series sequence are 102 and 103, 103 and 104, respectively. First, obtain the variances of 102 and 103, and the variances of 103 and 104, respectively, and then obtain the mean of the variances as the mean of the power variances of the data points on the right side of each position of the unit power 101 in the power demand time series sequence.

[0049] After obtaining the importance of the left side of the unit power based on the above steps, continue to perform the following steps to determine the importance of the right side of the unit power.

[0050] For example, the importance of determining the right side of the unit power can be specifically referred to the following relationship:

[0051] ;

[0052] In the formula, represents the importance of the right side of the i-th unit power, represents the mean value of the power variance of the data points on the left side of the i-th unit power in the power demand time series, represents the mean value of the power variance of the data points on the right side of the i-th unit power in the power demand time series, represents the power demand value of the i-th unit power, It represents the mean of the power means of the data points on the right side of the i-th unit power in the power demand time series. Represents the absolute value symbol.

[0053] In the above formula, It indicates the relative size of the change on the right side of the i-th unit power. The larger the value is, the greater the change in the power demand of the welding engineering vehicle on the right side of the i-th unit power is, the more complex the trend is, the more difficult it is to predict subsequent data through the data on the right side of the unit power, and the higher the importance of the i-th unit power is.

[0054] It represents the relative gap between the data mean on the right side of the i-th unit power in the power demand time series and the power demand value of the i-th unit power. The larger the value is, the more prominent the i-th unit power is, the more difficult it is to predict, and the higher the corresponding importance is.

[0055] After obtaining the importance of the left and right sides of the unit power based on the above steps, the left change weight and the right change weight can be obtained based on the proportion of the importance of the left and right sides in the total importance value, and the importance of the unit power can be obtained through the left and right side change weights of each unit power to achieve accurate division of the state interval.

[0056] Specifically, when determining the importance of a unit power, the total number of types of adjacent unit powers on both sides of the unit power in the power demand time series may be first obtained.

[0057] Take an example to illustrate how to obtain the number of unit power types: the power demand time series is {104, 101, 102, 103, 101, 103, 101, 104}, then the adjacent unit powers on the left of the i-th unit power 101 are 104, 103, 103 respectively, and the corresponding number of types is is 2, and the adjacent unit powers on the right of unit power 101 are 102, 103, and 104 respectively. The corresponding number of types is 3, the number of types of adjacent unit powers on the left and right sides of unit power 101 is 5.

[0058] For example, in the embodiment of the present invention, the importance of unit power is determined, and specifically, the following relationship can be referred to:

[0059] ;

[0060] In the formula, represents the importance of the i-th unit power, It represents the total number of types of adjacent unit powers on the left and right sides of the i-th unit power in the power demand time series. Indicates the total number of types corresponding to the unit power with the highest number of occurrences in the power demand time series. , They represent the left and right change weights of the i-th unit power, respectively. , They represent the number of adjacent unit powers on the left and right of the i-th unit power in the power demand timing sequence, Indicates the total number of types of unit power.

[0061] In the above formula, It indicates the relative size of the number of times the i-th unit power appears in the power demand timing sequence. The larger the value is, the more times the i-th unit power appears in the power demand timing sequence. The higher the ratio to the maximum number is, the higher the corresponding importance is.

[0062] and The larger it is, the more complex the change of the i-th unit power in the power demand time series is, the more difficult the subsequent prediction is, and the higher the corresponding importance is.

[0063] Based on the above steps, the changes in the data on the left and right sides of each position of the unit power in the power demand time series are analyzed, and after the importance of each unit power is accurately obtained, the following steps are continued.

[0064] S3: The prominence of the unit power is obtained by the deviation between the importance of the unit power and the importance of the adjacent unit power in the power demand interval.

[0065] It should be noted that before using the hidden Markov model to predict the power demand of welding engineering vehicles, the state interval cannot be directly obtained by dividing the importance of each unit power. This is because the accuracy of the number of state intervals directly obtained by dividing the importance of each unit power is low. Too many state intervals will cause the computational complexity of the state transfer matrix in the hidden Markov model; too small a number of state intervals will lead to low prediction accuracy, thereby affecting the subsequent prediction accuracy.

[0066] Based on this, the embodiment of the present invention can analyze the prominence of the importance of each unit power and set a finer division for the unit power with a more prominent importance, so as to capture more subtle changes in power demand.

[0067] For example, in the embodiment of the present invention, the prominence of the unit power is determined, and the following relationship can be specifically referred to:

[0068] ;

[0069] In the formula, represents the prominence of the i-th unit power, , , Respectively represent the i-th and , The importance of a unit of power, represents the mean importance of all unit powers, Represents the absolute value symbol.

[0070] In the above formula, Indicates the i-th unit power relative to the The greater the value, the more prominent the importance of the i-th unit power is relative to the The more important a unit power is, the smaller its state interval needs to be for more detailed analysis. Indicates the i-th unit power relative to the The greater the value, the more prominent the importance of the i-th unit power is relative to the The more important a unit power is, the smaller its state interval needs to be for more detailed analysis.

[0071] In this way, the embodiment of the present invention obtains the comparison result between the importance of the unit power and the unit powers on the left and right sides of its power demand interval, and corrects the importance of the unit power, so as to accurately obtain the prominence of the importance of the unit power. Through the prominence of each unit power, the division of the state interval can be accurately realized, so as to accurately obtain the power demand forecast value required by the welding engineering vehicle, that is, continue to execute the following steps.

[0072] S4: Divide the power demand interval according to the prominence of each unit power to assist in the allocation of the extended-range power source for welding engineering vehicles.

[0073] It should be noted that, based on the above steps, the prominence of each unit power can be accurately obtained, and the division of the state interval can be accurately achieved through the prominence of each unit power.

[0074] By way of example, in an embodiment of the present invention, the power demand interval is divided according to the prominence of each unit power, including: dividing the power demand interval into multiple initial state intervals according to each unit power, one unit power corresponding to one initial state interval; presetting a fusion threshold; taking the initial state interval corresponding to the unit power having a prominence less than the fusion threshold as the state interval to be fused, obtaining the minimum prominence corresponding to the adjacent initial state intervals on the left and right sides of the state interval to be fused in the power demand interval, fusing the state interval to be fused with the initial state interval corresponding to the minimum prominence to obtain a state interval, and finally dividing the power demand interval into multiple state intervals.

[0075] The fusion threshold may be preset to 0.2; the fusion threshold may be specifically set according to actual needs, and the embodiment of the present invention does not impose too many restrictions on this.

[0076] It can be understood that the minimum prominence corresponding to the adjacent initial state intervals on the left and right sides is the smaller prominence in the unit power corresponding to the adjacent initial state intervals on the left and right sides.

[0077] Take an example to illustrate the fusion of initial state intervals: the current prominence of unit power is 0.19, and the initial state interval corresponding to this unit power is the state interval to be fused. The prominences of unit power corresponding to the adjacent initial state intervals on the left and right sides of the state interval to be fused are 0.3 and 0.15 respectively. The current state interval to be fused is fused with the initial state interval with a prominence of 0.15 to obtain a state interval.

[0078] Based on this, the power demand interval can be divided into multiple state intervals, and the power demand of the welding engineering vehicle can be predicted based on the state intervals.

[0079] For example, in an embodiment of the present invention, the power demand interval is divided according to the prominence of each unit power to assist in the allocation of the extended-range power source for the welding engineering vehicle, including: processing the state interval of the vehicle's power demand at the current moment through a hidden Markov model to obtain the state interval of the vehicle's power demand prediction value, using the power demand mean of the state interval as the vehicle's power demand prediction value, and allocating power to the welding engineering vehicle according to the power demand prediction value.

[0080] Specifically, when the state interval of the vehicle's power demand at the current moment is processed by the hidden Markov model to obtain the state interval of the vehicle's power demand prediction value, various parameters can be obtained through the power demand time series, including the initial matrix, the state transfer matrix and the emission matrix, etc.; based on the state interval of the vehicle's power demand at the current moment, the probability of being in each possible state interval next is determined through the initial matrix, and the probability of transferring from the current state interval to each possible state interval is calculated through the state transfer matrix, and then combined with the emission matrix to finally obtain the probability of each possible state interval next, and the possible state interval with the largest probability is the state interval where the welding engineering vehicle power demand prediction value is located.

[0081] The specific steps of processing the state interval of the vehicle's power demand at the current moment by using the hidden Markov model to obtain the state interval of the vehicle's power demand prediction value can be achieved by existing technologies, and the embodiments of the present invention are not described in detail here.

[0082] Take an example to illustrate how to obtain the next power demand forecast value through the state interval of the vehicle's power demand at the current moment: if the power demand at the current moment is 100, which belongs to the state interval {99, 100, 101}, the state interval {99, 100, 101} is processed by the hidden Markov model to obtain the next state interval {104, 105, 106}, then the average value of the unit power in this state interval, 105, is taken as the power demand forecast value of the welding engineering vehicle.

[0083] After the power demand prediction value of the welding engineering vehicle is obtained based on the above steps, the power source can be allocated to the welding engineering vehicle based on the power demand prediction value.

[0084] For example, when allocating power sources, the inner control uses a dynamic programming algorithm to process the power demand prediction value to obtain the power battery reference target power and the fuel cell reference target power. The outer control corrects the fuel cell reference target power according to the fuel cell system voltage decay model, thereby realizing the allocation of power sources for the welding engineering vehicle.

[0085] The specific steps of allocating power sources to the welding engineering vehicle according to the power demand prediction value can be implemented by the existing technology, and the embodiments of the present invention will not be described in detail here.

[0086] It should be further explained that the power demand prediction value of the welding engineering vehicle cannot exceed the safety range. Abnormal power demand may mean that the welding engineering vehicle is in poor working condition or has potential failures. Based on this, the obtained power demand prediction value can be monitored for abnormalities.

[0087] For example, in an embodiment of the present invention, a power demand prediction value of a vehicle is obtained, and then the method further includes: performing abnormality monitoring on the power demand prediction value of the vehicle.

[0088] In this way, by monitoring the abnormality of the power demand forecast value, the potential failure points of the equipment can be discovered in time, and preventive maintenance can be performed before the failure occurs, thus reducing the frequency of equipment failure.

[0089] It can be seen that in the embodiment of the present invention, when realizing the power source allocation of the welding engineering vehicle, the power demand values ​​appearing in the vehicle power demand time series sequence can be sorted from large to small to obtain the power demand interval, and each power demand value in the power demand interval can be recorded as unit power; the left change weight and the right change weight of the unit power are obtained by the data changes on the left and right sides of each position of the unit power in the power demand time series sequence; the importance of the unit power is calculated; the prominence of the unit power is obtained by the deviation between the importance of the unit power and the importance of the adjacent unit power in the power demand interval; the power demand interval is divided according to the prominence of each unit power to assist in realizing the allocation of the extended-range power source for the welding engineering vehicle.

[0090] In this way, the embodiment of the present invention realizes the power demand prediction of the welding engineering vehicle through the hidden Markov model, thereby realizing the accurate allocation of the power source. In this process, the embodiment of the present invention takes into account that when the power demand interval is divided into state intervals, the fixed-size state intervals do not take into account the changes of each unit power, resulting in the low accuracy of the power demand prediction result. Based on this, the embodiment of the present invention obtains the data changes on the left and right sides of each position of the unit power in the vehicle power demand time series sequence, accurately obtains the importance of the unit power, and effectively improves the accuracy of the state interval division; on this basis, the embodiment of the present invention also takes into account that when the state interval division is directly based on the importance, the state interval division accuracy corresponding to some unit powers is low. Based on this, the embodiment of the present invention further obtains the prominence of the importance of each unit power, and realizes the accurate division of the state interval according to the prominence of the importance, effectively improving the accuracy of the power demand prediction of the welding engineering vehicle, thereby effectively improving the accuracy of the power source allocation.

[0091] An embodiment of the present invention also discloses an extended-range power source distribution optimization system for a welding engineering vehicle, including a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, an extended-range power source distribution optimization method for a welding engineering vehicle according to the present invention is implemented.

[0092] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0093] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM, a dynamic random access memory DRAM, a static random access memory SRAM, an enhanced dynamic random access memory EDRAM, a high bandwidth memory HBM, a hybrid memory cube HMC, etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device.

[0094] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0095] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for optimizing the distribution of extended-range power sources for welding engineering vehicles, characterized in that: include: The power demand values ​​appearing in the vehicle power demand time series are sorted from large to small to obtain a power demand interval, and each power demand value in the power demand interval is recorded as a unit power; Obtaining a left-side change weight and a right-side change weight of the unit power through changes in the left and right-side data of the unit power at each position in the power demand time series; Calculate the importance of the unit power: ; In the formula, represents the importance of the i-th unit power, It represents the total number of types of adjacent unit powers on the left and right sides of the i-th unit power in the power demand time series. Indicates the total number of types corresponding to the unit power with the highest number of occurrences in the power demand time series. , They represent the left and right change weights of the i-th unit power, respectively. , They represent the number of adjacent unit powers on the left and right of the i-th unit power in the power demand timing sequence, Indicates the total number of types of unit power; obtains the prominence of the unit power by the degree of deviation between the importance of the unit power and the importance of adjacent unit powers in the power demand interval; The power demand interval is divided according to the prominence of each unit power to assist in the allocation of the extended-range power source for the welding engineering vehicle.

2. The method for optimizing the distribution of extended-range power sources for welding engineering vehicles according to claim 1, characterized in that: The power demand values ​​appearing in the vehicle power demand time series are sorted from large to small, and the process also includes: The power required by the welding engineering vehicle during operation is collected, and the power demand value collected at each moment is arranged in time series as a data point to obtain a power demand time series sequence.

3. The method for optimizing the distribution of extended-range power sources for welding engineering vehicles according to claim 2, characterized in that: The obtaining of the left side change weight and the right side change weight of the unit power includes: Importance of calculating the left side of the unit power ; In the formula, represents the mean value of the power variance of the data points on the left side of the i-th unit power in the power demand time series, represents the mean value of the power variance of the data points on the right side of the i-th unit power in the power demand time series, represents the power demand value of the i-th unit power, It represents the mean of the power means of the data points on the left side of the i-th unit power in the power demand time series. It obtains the sum of the importance of the left and right sides of the unit power, and takes the ratio of the left importance to the sum as the left change weight, and takes the ratio of the right importance to the sum as the right change weight.

4. The method for optimizing the distribution of extended-range power sources for welding engineering vehicles according to claim 1, characterized in that: The prominence of the unit power satisfies the relationship: ； In the formula, represents the prominence of the i-th unit power, , , Respectively represent the i-th and , The importance of a unit of power, represents the mean importance of all unit powers, Represents the absolute value symbol.

5. The method for optimizing the distribution of extended-range power sources for welding engineering vehicles according to claim 1, characterized in that: The dividing of the power demand intervals according to the prominence of each unit power includes: Dividing the power demand interval into a plurality of initial state intervals by each unit power, wherein one unit power corresponds to one initial state interval; Preset a fusion threshold; take the initial state interval corresponding to the unit power with a prominence less than the fusion threshold as the state interval to be fused, obtain the minimum prominence corresponding to the adjacent initial state intervals on the left and right sides of the state interval to be fused in the power demand interval, fuse the state interval to be fused with the initial state interval corresponding to the minimum prominence to obtain the state interval, and finally divide the power demand interval into multiple state intervals.

6. The method for optimizing the distribution of extended-range power sources for welding engineering vehicles according to claim 5, characterized in that: The power demand interval is divided according to the prominence of each unit power to assist in the allocation of the extended-range power source for the welding engineering vehicle, including: The state interval of the vehicle's power demand at the current moment is processed by the hidden Markov model to obtain the state interval of the vehicle's power demand prediction value. The power demand mean of the state interval is used as the vehicle's power demand prediction value, and power is allocated to the welding engineering vehicle according to the power demand prediction value.

7. The method for optimizing the distribution of extended-range power sources for welding engineering vehicles according to claim 6, characterized in that: The method further includes allocating power to the welding engineering vehicle according to the power demand prediction value, and then: The predicted power demand value of the vehicle is monitored for abnormalities.

8. An extended-range power source distribution optimization system for a welding engineering vehicle, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a method for optimizing the distribution of an extended-range power source for a welding engineering vehicle according to any one of claims 1 to 7 is implemented.

Images