Power distribution network primary and secondary fusion coordination model and method of power system

Abstract

The invention relates to a power distribution network primary and secondary fusion coordination model and method of a power system, belongs to the technical field of primary and secondary fusion coordination, can achieve maneuvering and active sampling speed configuration, efficiently improves the measurement sensitivity and instantaneity of abnormal fluctuation of a fusion value, and particularly provides a power distribution network primary and secondary fusion coordination model and method when the fusion value of a switch rapidly changes or is hidden in anomalies. The measuring unit can actively improve the sampling speed, guarantee the real-time mastering of important fusion values and weaken the hidden danger of lagging measurement, and the real-time speed control not only improves the early finding rate of switch faults, but also provides more accurate fault sampling for high-hidden-danger switches, and is suitable for early maintenance and convenient to use. Therefore, the hidden danger of switch damage or accidents is reduced, and finally the reliability of the switch and the high efficiency of switch fault management and control are obviously improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of primary and secondary fusion coordination, and specifically relates to a primary and secondary fusion coordination model and method for a distribution network of an electric power system. Background Art

[0002] The distribution network refers to a power grid that collects electric energy from the transmission network or regional power plants and distributes it locally or step by step according to voltage to various users through distribution facilities. It is composed of overhead lines, cables, towers, distribution transformers, disconnectors, reactive power compensators and some ancillary facilities, and plays an important role in distributing electric energy in the power grid.

[0003] In the distribution network, along with the introduction of primary and secondary fusion switches, it is often necessary to use the wireless communication connection between the online measuring machine and the host computer in the prior art solution with the patent publication number "CN214895503U". The measuring unit in the online measuring machine is connected to the main controller. The measuring unit is used to sample the voltage and current values ​​of the primary and secondary fusion switches in the distribution network and transmit them to the main controller. The main controller is used to transmit the collected voltage and current values ​​of the primary and secondary fusion switches in the distribution network to the host computer for display. The voltage value or current value of the primary and secondary fusion switch in the distribution network is the primary and secondary fusion value of the distribution network.

[0004] At present, when performing fusion value sampling, a pre-defined starting sampling speed (the sampling speed is how many times the primary and secondary fusion values ​​of the distribution network are sampled per second) is generally used to perform the primary and secondary fusion value sampling of the distribution network. The starting sampling speed can meet reasonable sampling requirements. In the face of a faulty primary and secondary fusion switch, when the fusion value of the switch has hidden anomalies causing the fusion value to fluctuate rapidly, if the pre-defined starting sampling speed is still used, the abnormal fluctuation of the fusion value often cannot be grasped in time, resulting in switch failure, which cannot be measured in time. Delayed measurement often loses important maintenance opportunities, causing the switch failure to become more serious, and even causing serious switch line accidents, such as switch line fire accidents. Summary of the invention

[0005] In order to solve the defects in the prior art, the present invention proposes a primary and secondary fusion coordination model and method for the distribution network of the power system, which can achieve flexible and active sampling speed configuration, and effectively improve the measurement sensitivity and timeliness of abnormal fluctuations in the fusion value. Especially when the fusion value of the switch shows rapid changes or hidden anomalies, the measurement unit can actively improve the sampling speed to ensure the real-time grasp of important fusion values ​​and reduce the hidden dangers of delayed measurement. Such real-time speed control not only improves the early detection rate of switch faults, but also provides more accurate fault sampling for high-risk switches, which is suitable for early maintenance, thereby reducing the hidden dangers of switch damage or accidents, and ultimately significantly improving the reliability of the switch and the efficiency of switch fault management.

[0006] The present invention utilizes the following technical solutions.

[0007] A primary and secondary integration coordination method for a distribution network of an electric power system, comprising:

[0008] The measuring unit samples the voltage and current values ​​of the primary and secondary fusion switches in the distribution network and transmits them to the main controller. The main controller transmits the collected voltage and current values ​​of the primary and secondary fusion switches in the distribution network to the host computer for display and analysis. The voltage or current value of the primary and secondary fusion switch in the distribution network is the primary and secondary fusion value of the distribution network.

[0009] The method in which the main controller transmits the collected voltage and current values ​​of the primary and secondary fusion switches in the distribution network to the upper computer for analysis includes:

[0010] Step 1: According to the requirements of sampling the fusion value under the reasonable operation condition of the primary and secondary fusion switch, define a starting sampling speed for the measurement unit, perform the sampling of the primary and secondary fusion value of the distribution network at the starting sampling speed, and transmit the sampled primary and secondary fusion value of the distribution network to the host computer;

[0011] Step 2: After sampling the primary and secondary fusion values ​​of the distribution network, the host computer extracts attributes of the primary and secondary fusion values ​​of the distribution network, and parses the extracted attributes. The analyzed attributes are used to estimate the change status of the primary and secondary fusion values ​​of the distribution network through a deep learning model, and an overall evaluation is performed on the change status of the primary and secondary fusion values ​​of the distribution network;

[0012] Step 3: Based on the estimated values, the integrated value changes are divided into different modes, including reasonable changes and rapid changes;

[0013] Step 4: In the face of changes in the fusion value under reasonable changes, the initial sampling speed is used to perform the first and second fusion value sampling of the distribution network. If the measurement unit confirms that the fusion value change of the switch is in a rapid change state, the initial sampling speed is used as a condition to perform flexible control on the specific sampling speed.

[0014] Furthermore, in step 1, a starting sampling speed is initially defined for the measuring unit, and the speed is defined based on the requirements of the fusion value fluctuation under the reasonable operating conditions of the primary and secondary fusion switch. After the measuring unit is running, the primary and secondary fusion values ​​of the distribution network of the primary and secondary fusion switch are sampled in real time according to the pre-defined starting sampling speed. The primary and secondary fusion values ​​of the distribution network are then transmitted to the host computer via the main controller.

[0015] Furthermore, in step 2, the value after attribute extraction includes the deviation amplitude of the current fusion value and the reasonable standard fusion value of the switch and the sudden change of the fusion value in a short period of time. After obtaining the value after attribute extraction, during the measured time period, the deviation amplitude of the current fusion value and the reasonable standard fusion value of the switch and the sudden change of the fusion value in a short period of time are analyzed to form the fusion value deviation parameter and the sudden change fusion value parameter respectively, and the fusion value deviation parameter and the sudden change fusion value parameter are sent to the deep learning model after pre-learning, and the fusion value dynamic change parameter is formed through the deep learning model, and the change of the primary and secondary fusion values ​​of the distribution network is comprehensively evaluated through the fusion value dynamic change parameter.

[0016] Further, in step 2, the deep learning model after prior learning is a method model that has been constructed and improved through learning of past numerical values ​​and corresponding attributes. The deep learning model after prior learning receives the input fusion value bias parameters and sudden change fusion value parameters, and forms fusion value dynamic change parameters.

[0017] Furthermore, in step 2, the learning method includes:

[0018] First, a number of past primary and secondary integrated values ​​of the distribution network are obtained as past values. The number of past primary and secondary integrated values ​​of the distribution network include integrated value change properties under various different conditions, including reasonable standard integrated values ​​and sudden change integrated values ​​during sudden changes.

[0019] Then, the attribute extraction is performed on the primary and secondary fusion values ​​of several past distribution networks. The fusion value deviation parameters and the sudden change fusion value parameters after attribute extraction are used as the attributes of the input model, and the Gaussian mixture model is used to input the past values ​​into the model for learning;

[0020] The final model is stored and used in real-time analysis. When new distribution network primary and secondary fusion values ​​are input, the model is estimated or grouped according to the previously learned model.

[0021] Furthermore, in step 2, in a predefined measurement period, the method of analyzing the deviation amplitude of the current fusion value and the switch reasonable standard fusion value to form the fusion value deviation parameter includes:

[0022] During the measurement period, the current distribution network primary and secondary fusion value IS of the switch is initially sampled. dvssfou , I.S. dvssfou Defined as the fusion value representing the current sampling, synchronous, and reasonable standard fusion value IS of the switch cbtfmjpf , I.S. cbtfmjpf Defined as the standard fusion value that represents the reasonable condition of the switch;

[0023] Calculate the fusion value deviation between the current fusion value and the standard fusion value;

[0024] Compute the fusion value bias parameter.

[0025] Furthermore, the equation for calculating the fusion value bias parameter is: ISEJ υ =ΔIS*U x , in the equation, ISEJ υ Characterizes the bias parameter of the fusion value.

[0026] Furthermore, in step 2, during the measured period, the method of analyzing the sudden change of the fusion value of the switch in a short period of time to form a sudden change fusion value parameter includes:

[0027] During the measurement period, the fusion value change level is calculated for each pair of continuous primary and secondary fusion value points of the distribution network. The calculation equation of the fusion value change level is: In the equation, H j Represents the level of change of the fusion value at time j, IS j With IS j+1 Respectively represent the fusion value at time j and j+1, Δu j Characterizes the size of the time period between time j and j+1;

[0028] In the measured period, after calculating the fusion value changes at each moment through the hierarchy, the instantaneous total function of the change is calculated. The calculation equation is: D j Represents the total function value at time j, H l represents the level of change of the fusion value calculated at time l, β represents the attenuation parameter, P represents the total number of numerical points in the measured time period, and e is the Euler number;

[0029] The calculation equation for the sudden change in the fusion value parameter of the entire measurement period is: In the equation, ISTJ ν The fusion value parameter that characterizes the sudden change, D j Characterizes the total function value at time j.

[0030] Furthermore, the equation for calculating the deviation of the fusion value between the current fusion value and the standard fusion value is: ΔIS represents the deviation value of the enhanced fusion value.

[0031] Import the criticality parameters of the time period and perform configuration according to the duration of the time period when the fusion value deviates continuously;

[0032] Fusion value maneuvering variable parameter Ezpbnjd ifbsu The resulting operational equation is: In the equation, ζ1 and ζ2 are the fusion value bias parameters ISEJ υISTJ with the fusion value parameter of sudden change ν The pre-defined ratio parameter, and both ζ1 and ζ2 are higher than zero.

[0033] Furthermore, the operation equation of the time period criticality parameter is: U x Characterize the criticality parameter of the time period, u efwjbujpq Characterizes the duration of the fusion value deviation, U xjoepx Characterizes the size of the time period being measured.

[0034] Furthermore, in step 3, the fusion value maneuvering change parameter estimated according to the deep learning model is compared and analyzed with the standard critical value of the fusion value maneuvering change parameter defined in advance, and the fusion value change is cut into different modes, and the method includes:

[0035] If the fusion value maneuvering change parameter is not lower than the fusion value maneuvering change parameter standard critical value, the fusion value change in the measured time period is cut into a rapid change state;

[0036] If the fusion value maneuvering change parameter is lower than the standard critical value of the fusion value maneuvering change parameter, the fusion value change within the measured time period is cut into reasonable change conditions.

[0037] Furthermore, in step 4, in the face of the change of the fusion value under the rapidly changing condition, the initial sampling speed is used as a condition to perform a motorized control on the specific sampling speed, and the method includes:

[0038] According to the fusion value, the variable parameter Ezpbnjd is automatically changed ifbsu and fusion value maneuvering variable parameter standard critical value θ Ezpbnjd The relationship between them is used to calculate the control parameters. The calculation equation is: S represents the control parameter, which is used to configure the specific sampling speed, η represents the configuration parameter, and χ represents the gain parameter;

[0039] After obtaining the control parameter S, the sampling speed multiplier is calculated. The calculation equation is: Δg represents the sampling speed multiplier, that is, the value to be increased on the initial sampling speed, g0 represents the initial sampling speed, and ξ represents the importance parameter;

[0040] According to the calculated sampling speed multiplier, calculate the specific sampling speed. The calculation equation is: g bduvbm =g0*Δg, in the equation, g bduvbm Characterize the specific sampling speed after manipulation;

[0041] The measuring unit configures the sampling speed to a specific sampling speed via an initial sampling speed, and performs sampling on the primary and secondary fusion values ​​of the switch's distribution network at the specific sampling speed.

[0042] A primary and secondary integrated coordination mode of a distribution network of a power system, comprising:

[0043] The online measuring machine is wirelessly connected to the host computer. The measuring unit in the online measuring machine is connected to the main controller. The measuring unit is used to sample the voltage and current values ​​of the primary and secondary fusion switches in the distribution network and transmit them to the main controller. The main controller is used to transmit the collected voltage and current values ​​of the primary and secondary fusion switches in the distribution network to the host computer for display and analysis. The voltage or current value of the primary and secondary fusion switch in the distribution network is the primary and secondary fusion value of the distribution network.

[0044] The modules running on the host computer include:

[0045] A definition module is used to define a starting sampling speed for the measurement unit according to the requirements of sampling the fusion value under the reasonable operation condition of the primary and secondary fusion switch, perform the sampling of the primary and secondary fusion value of the distribution network at the starting sampling speed, and transmit the sampled primary and secondary fusion value of the distribution network to the upper computer;

[0046] The evaluation module is used for the host computer to extract attributes of the primary and secondary fusion values ​​of the distribution network after sampling them, and to analyze the extracted attributes, and to estimate the change status of the primary and secondary fusion values ​​of the distribution network through the deep learning model of the analyzed attributes, and to perform an overall evaluation on the change status of the primary and secondary fusion values ​​of the distribution network;

[0047] The cutting module is used to cut the fusion value changes into different modes according to the estimated values, including reasonable change conditions and rapid change conditions;

[0048] The control module is used to face the changes in the fusion value under reasonable changes. It uses the initial sampling speed to perform the first and second fusion value sampling of the distribution network. If the measurement unit confirms that the fusion value change of the switch is in a rapid change state, the initial sampling speed is used as a condition to perform flexible control on the specific sampling speed.

[0049] The beneficial effects of the present invention are that, compared with the prior art, the technical effects of the present invention include:

[0050] It can achieve flexible and active sampling speed configuration, effectively improving the measurement sensitivity and timeliness of abnormal fluctuations in the integrated value. Especially when the integrated value of the switch shows rapid changes or hidden abnormalities, the measurement unit can actively improve the sampling speed to ensure the real-time grasp of important integrated values ​​and reduce the risk of delayed measurement. This kind of real-time speed control not only improves the early detection rate of switch faults, but also provides more accurate fault sampling for high-risk switches, which is convenient for early maintenance, thereby reducing the risk of switch damage or accidents, and ultimately significantly improving the reliability of the switch and the efficiency of switch fault control. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is a partial flow chart of the primary and secondary integration coordination method of the distribution network of the power system described in the present invention;

[0052] Figure 2 It is a partial structural diagram of the primary and secondary fusion coordination model of the distribution network of the power system described in the present invention. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solution and advantages of the present invention clearer, the following will be combined with the drawings in the embodiments of the present invention to clearly and completely express the technical solution of the present invention. The embodiments expressed in this application are only some embodiments of the present invention, not all embodiments. According to the spirit of the present invention, other embodiments obtained by ordinary technicians in this field without making creative work are all within the protection scope of the present invention.

[0054] like Figure 1 As shown, the primary and secondary integration coordination method of a distribution network of a power system according to the present invention comprises:

[0055] The measuring unit samples the voltage and current values ​​of the primary and secondary fusion switches in the distribution network and transmits them to the main controller. The main controller transmits the collected voltage and current values ​​of the primary and secondary fusion switches in the distribution network to the host computer for display and analysis. The voltage or current value of the primary and secondary fusion switch in the distribution network is the primary and secondary fusion value of the distribution network.

[0056] The method in which the main controller transmits the collected voltage and current values ​​of the primary and secondary fusion switches in the distribution network to the upper computer for analysis includes:

[0057] Step 1: According to the requirements of sampling the fusion value under the reasonable operation condition of the primary and secondary fusion switch, define a starting sampling speed for the measurement unit (the sampling speed is how many times the primary and secondary fusion value of the distribution network is sampled per second), perform the sampling of the primary and secondary fusion value of the distribution network at the starting sampling speed, and transmit the sampled primary and secondary fusion value of the distribution network to the host computer;

[0058] In a preferred but non-limiting embodiment of the present invention, in step 1, a starting sampling speed is initially defined for the measuring unit. This speed is often defined based on the requirements for fluctuations in the fusion value under reasonable operating conditions of the primary and secondary fusion switch, and can meet the general requirements of conventional sampling. The starting sampling speed should be large enough to grasp the changes in the fusion value of the primary and secondary fusion switch under normal operation, and should not waste energy consumption and the amount of software and hardware tasks used for calculations. After the measuring unit is running, the primary and secondary fusion values ​​of the distribution network of the primary and secondary fusion switch are sampled in real time according to the pre-defined starting sampling speed, and the primary and secondary fusion values ​​of the distribution network are then transmitted to the host computer via the main controller.

[0059] Step 2: After sampling the primary and secondary fusion values ​​of the distribution network, the host computer extracts attributes of the primary and secondary fusion values ​​of the distribution network, and parses the extracted attributes. The analyzed attributes are used to estimate the change status of the primary and secondary fusion values ​​of the distribution network through a deep learning model, and an overall evaluation is performed on the change status of the primary and secondary fusion values ​​of the distribution network;

[0060] In a preferred but non-restrictive embodiment of the present invention, in step 2, the value after attribute extraction includes the deviation amplitude of the current fusion value and the reasonable standard fusion value of the switch and the sudden change of the fusion value in a short period of time. After obtaining the value after attribute extraction, during the measured time period, the deviation amplitude of the current fusion value and the reasonable standard fusion value of the switch and the sudden change of the fusion value in a short period of time are analyzed to form fusion value deviation parameters and sudden change fusion value parameters respectively, and the fusion value deviation parameters and the sudden change fusion value parameters are sent to the deep learning model after pre-learning, and the fusion value dynamic change parameters are formed through the deep learning model, and the change status of the primary and secondary fusion values ​​of the distribution network is comprehensively evaluated through the fusion value dynamic change parameters.

[0061] In a preferred but non-limiting embodiment of the present invention, in step 2, the deep learning model after prior learning is a method model that has been constructed and improved through learning of past values ​​and corresponding attributes, and is used to estimate or group new values. The deep learning model after prior learning receives the input fusion value bias parameters and the sudden change fusion value parameters, and forms the fusion value dynamic change parameters.

[0062] In a preferred but non-limiting embodiment of the present invention, in step 2, the learning method includes:

[0063] First, a number of past primary and secondary integrated values ​​of the distribution network are obtained as past values. The number of past primary and secondary integrated values ​​of the distribution network include integrated value change properties under various different conditions, including reasonable standard integrated values ​​and sudden change integrated values ​​during sudden changes.

[0064] Then, the attribute extraction is performed on the obtained primary and secondary fusion values ​​of several past distribution networks. The fusion value deviation parameters and the sudden change fusion value parameters after attribute extraction are used as the attributes of the input model. The Gaussian mixture model is used to input the marked past values ​​into the model for learning. The learning process is to repeatedly change the model parameters to minimize the estimation error, so that the model can accurately grasp the traceability and abnormality of the fusion value changes. After the learning is completed, the model is evaluated to ensure that its estimation of new values ​​has high accuracy.

[0065] The final model is stored and used in real-time analysis. When a new distribution network primary and secondary fusion value is sent, the model is estimated or grouped according to the previously learned model. The deep learning model collects the fusion value deviation parameters and the sudden change fusion value parameters to form the fusion value dynamic change parameters, which is suitable for overall evaluation of the change status of the distribution network primary and secondary fusion values. The fusion value dynamic change parameters take into account the deviation amplitude of the switch fusion value relative to the reasonable standard and the sudden change in the short term, so as to provide more comprehensive fault sampling and hidden danger early warning. Through this method, the deep learning model can identify hidden fault hazards in the complex distribution network primary and secondary fusion values, and provide real-time and efficient information assistance to switches and maintainers.

[0066] When the deviation amplitude of the previous fusion value of the switch and its reasonable standard fusion value is not small, it often indicates that the fusion value of the switch fluctuates greatly. Such deviation often reflects that the switch is facing abnormal current or voltage load, resulting in a strong increase or decrease in the fusion value. A large deviation often shows that the switch is undergoing too strong changes, such as poor contact, contact damage, spring fatigue, mechanical wear and even switch stop. The standard fusion value often represents the switch operation status of the primary and secondary fusion switch under stable conditions. Random and obvious deviations are often early warning signs of switch faults, and the manifestation requires sampling or immediate maintenance. Therefore, focusing on detecting the difference between the fusion value and the standard fusion value can help identify hidden fault hazards as soon as possible and provide timely feedback to ensure the reliability of the switch.

[0067] In a preferred but non-limiting embodiment of the present invention, in step 2, in a predefined measurement period, the method of analyzing the deviation amplitude of the current fusion value and the switch reasonable standard fusion value to form the fusion value deviation parameter includes:

[0068] During the measurement period, the current distribution network primary and secondary fusion value IS of the switch is initially sampled. dvssfou , I.S. dvssfou Defined as the fusion value representing the current sampling, synchronous, and reasonable standard fusion value IS of the switch cbtfmjpf , I.S. cbtfmjpf It is defined as the standard fusion value that represents the reasonable condition of the switch. It is the fusion value of the switch under stable conditions. The current primary and secondary fusion value of the switch is IS dvssfou A reasonable standard fusion value with the switch IS cbtfmjpf For later analysis;

[0069] The current primary and secondary fusion values ​​of the switch are often obtained in real time through the measurement unit.

[0070] To obtain a reasonable standard fusion value of the switch, continuous sampling must be carried out over a period of time. When the switch is in normal operation, the primary and secondary fusion values ​​of the distribution network are sampled several times. After eliminating abnormal fluctuations, the stable fusion value level of the switch is analyzed as a whole. This process often requires several days of sampling to ensure the accuracy and representativeness of the standard fusion value.

[0071] Calculate the fusion value deviation between the current fusion value and the standard fusion value;

[0072] In a preferred but non-limiting embodiment of the present invention, the equation for calculating the deviation of the fusion value between the current fusion value and the standard fusion value is: ΔIS represents the deviation of the enhanced fusion value, reflecting the difference between the current fusion value and the standard fusion value. cbtfmjof +1) is an enhancement parameter that represents the standard fusion value, which is used to enhance the sensitivity of the high fusion value segment and increase the tendency to rapid changes in the fusion value.

[0073] The effect of the duration of the fusion value deviation should be taken into account, and the key parameters of the time period should be imported, and the configuration should be performed according to the duration of the fusion value deviation.

[0074] In a preferred but non-limiting embodiment of the present invention, the operation equation of the time period criticality parameter is: U x Characterize the criticality parameter of the time period, u efwjbujpq Characterizes the duration of the fusion value deviation, U xjoepx Characterizes the size of the time period being measured.

[0075] Compute the fusion value bias parameter.

[0076] In a preferred but non-limiting embodiment of the present invention, the equation for calculating the fusion value bias parameter is: ISEJ υ =ΔIS*U x , in the equation, ISEJ υ Characterizes the bias parameter of the fusion value.

[0077] It can be understood from the fusion value deviation parameter that during the measured period, the deviation amplitude of the current fusion value and the reasonable standard fusion value of the switch is analyzed. The higher the value of the fusion value deviation parameter is, the higher the deviation amplitude of the current fusion value relative to the reasonable standard fusion value of the switch is, which often indicates that the fusion value fluctuation of the switch is more intense. A high fusion value deviation parameter often reflects that the switch has undergone obvious current or voltage load in a short period of time. At the same time, the value of the fusion value deviation parameter is not large, which indicates that the deviation between the current fusion value and the standard fusion value is not large, indicating that the fusion value is in a relatively stable state, and the current and voltage conditions of the switch are very stable.

[0078] When the fusion value of the switch changes suddenly in a short period of time, it often indicates that the fluctuation of the fusion value is very obvious. Such a strong sudden change indicates that the switch has experienced an abnormal load increase or load reduction in a very short period of time. Therefore, the switch is often faced with a strong load increase or load reduction phenomenon, and it often shows unstable switch performance. For example, a strong sudden change in the fusion value is often caused by a sudden change in load, or a more serious situation is like poor contact. When such a situation occurs, the switch must effectively adapt to the new situation. If the switch cannot be configured in time, it often causes voltage and current instability, and even causes fire or switch stop. Therefore, the sudden change in the fusion value in a short period of time is not only a manifestation of switch load increase or load reduction, but also an early warning sign of hidden faults, which should be paid special attention to.

[0079] In a preferred but non-limiting embodiment of the present invention, in step 2, during the measured period, the method of analyzing the sudden change of the fusion value of the switch in a short period of time to form a sudden change fusion value parameter includes:

[0080] During the measurement period, the fusion value change level is calculated for each pair of continuous distribution network primary and secondary fusion value points (distribution network primary and secondary fusion value points are distribution network primary and secondary fusion values ​​arranged in the order of sampling time). The calculation equation of the fusion value change level is: In the equation, H j Represents the level of change of the fusion value at time j, IS j With IS j+1 Respectively represent the fusion value at time j and j+1, Δu j Characterize the time period between time j and j+1, use the square of the time period to make the time period have an obvious effect on the hierarchical operation, and tend to the sudden changes in the short term; time is the sampling time.

[0081] During the measured period, after calculating the fusion value changes at each moment through hierarchical calculation, the instantaneous total function of the changes is calculated to grasp the overall amplitude of the fusion value fluctuations. The calculation equation is: D j Represents the total function value at time j, H l represents the level of change of the fusion value calculated at time l, β represents the attenuation parameter, which is used to control the time sensitivity of the total function. A small value will reduce the amplitude of the previous value effect. j It can better reflect the current sudden changes. P represents the total number of numerical points in the measured period, and e is the Euler number.

[0082] The calculation equation for the sudden change in the fusion value parameter of the entire measurement period is: In the equation, ISTJ νThe parameter that characterizes the sudden change of the fusion value, that is, the amplitude of the strong fluctuation of the fusion value in the entire measurement period, D j Characterizes the total function value at time j.

[0083] The sudden change of the fusion value parameter can be understood. During the measured period, the sudden change of the fusion value of the switch in a short period of time is analyzed. The higher the value of the sudden change of the fusion value parameter, the more intense the fluctuation of the fusion value of the switch during the measured period. It indicates that the switch has undergone obvious changes in a short period of time. It is often caused by poor contact, contact damage, spring fatigue, mechanical wear fluctuations or hidden switch defects. When the sudden change of the fusion value parameter is not low, the sudden change of the fusion value is frequent and large, which often requires attention and maintenance. On the other hand, the lower the sudden change of the fusion value parameter, the more stable the fusion value is during the period, with little fluctuation, which often indicates that the switching state of the switch is very stable without obvious abnormal fluctuations.

[0084] Deep learning mode is optional and can achieve the ISEJ of the fusion value bias parameter υ ISEJ with sudden change in fusion value parameter υ Any deep learning model that performs overall analysis to form a fusion value and dynamically change parameters will do.

[0085] Fusion value maneuvering variable parameter Ezpbnjd ifbsu The resulting operational equation is: In the equation, ζ1 and ζ2 are the fusion value bias parameters ISEJ υ ISTJ with the fusion value parameter of sudden change ν The pre-defined ratio parameter, and both ζ1 and ζ2 are higher than zero.

[0086] It can be understood from the fusion value dynamic change parameter that during the measured time period, the higher the value of the fusion value deviation parameter formed after analyzing the deviation amplitude of the current fusion value and the reasonable standard fusion value of the switch, the higher the value of the sudden change fusion value parameter formed after analyzing the sudden change of the fusion value of the switch in a short period of time, that is, the higher the value of the fusion value dynamic change parameter formed during the measured time period, the stronger the fluctuation of the fusion value of the switch, otherwise, the more stable the fluctuation of the fusion value of the switch is.

[0087] Step 3: Based on the estimated values, the integrated value changes are divided into different modes, including reasonable changes and rapid changes;

[0088] In a preferred but non-limiting embodiment of the present invention, in step 3, the fusion value maneuvering change parameter estimated according to the deep learning model is compared and analyzed with the standard critical value of the fusion value maneuvering change parameter defined in advance, and the fusion value change is cut into different modes, and the method includes:

[0089] If the fusion value maneuvering change parameter is not lower than the fusion value maneuvering change parameter standard critical value, the fusion value change in the measured time period is cut into a rapid change state;

[0090] If the fusion value maneuvering change parameter is lower than the standard critical value of the fusion value maneuvering change parameter, the fusion value change within the measured time period is cut into reasonable change conditions.

[0091] Step 4: In the face of changes in the fusion value under reasonable changes, the initial sampling speed is used to perform the first and second fusion value sampling of the distribution network. If the measurement unit confirms that the fusion value change of the switch is in a rapid change state, the initial sampling speed is used as a condition to perform flexible control on the specific sampling speed to meet the first and second fusion value sampling requirements of the distribution network under rapid changes.

[0092] In a preferred but non-limiting embodiment of the present invention, in step 4, facing the change of the fusion value under the rapidly changing condition, the specific sampling speed is automatically controlled using the initial sampling speed as a condition, and the method includes:

[0093] According to the fusion value, the variable parameter Ezpbnjd is automatically changed ifbsu and fusion value maneuvering variable parameter standard critical value θ Ezpbnjd The relationship between them is used to calculate the control parameters. The calculation equation is: S represents the control parameter, which is used to configure the specific sampling speed, η represents the configuration parameter, which is used to control the sensitivity of the control parameter, and χ represents the gain parameter, which is used to control the feedback strength of the bias momentum;

[0094] After obtaining the control parameter S, the sampling speed multiplier is calculated. The calculation equation is: Δg represents the sampling speed multiplier, that is, the value to be increased on the initial sampling speed, g0 represents the initial sampling speed, and ξ represents the importance parameter, which is used to control the effect of the fusion value maneuvering parameter on the sampling speed multiplier;

[0095] According to the calculated sampling speed multiplier, calculate the specific sampling speed. The calculation equation is: g bduvbm =g0*Δg, in the equation, g bduvbm Characterizes the specific (i.e., real) sampling rate after manipulation;

[0096] After reaching the setting of the mobile configuration plan, the measurement unit immediately executes the plan, configures the sampling speed from the initial sampling speed to the specific sampling speed, and performs sampling on the primary and secondary fusion values ​​of the switch distribution network at the specific sampling speed;

[0097] After the setting of the flexible configuration plan is completed, the measurement unit immediately executes the plan to achieve flexible control of the specific sampling speed of the fusion value change under rapidly changing conditions, configure the sampling speed from the initial sampling speed to the specific sampling speed, and use the specific sampling speed to sample the primary and secondary fusion values ​​of the switch's distribution network to meet the sampling requirements of the primary and secondary fusion values ​​of the distribution network under rapidly changing conditions.

[0098] After the measurement unit determines that the fusion value fluctuation of the switch has been restored to a reasonable change state, the sampling speed is automatically restored to the initial sampling speed.

[0099] like Figure 2 As shown, the primary and secondary fusion coordination mode of a distribution network of a power system described in the present invention includes:

[0100] The online measuring machine is wirelessly connected to the host computer. The measuring unit in the online measuring machine is connected to the main controller. The measuring unit is used to sample the voltage and current values ​​of the primary and secondary fusion switches in the distribution network and transmit them to the main controller. The main controller is used to transmit the collected voltage and current values ​​of the primary and secondary fusion switches in the distribution network to the host computer for display and analysis. The voltage or current value of the primary and secondary fusion switch in the distribution network is the primary and secondary fusion value of the distribution network.

[0101] The modules running on the host computer include:

[0102] A definition module is used to define a starting sampling speed for the measurement unit according to the requirements of sampling the fusion value under the reasonable operation condition of the primary and secondary fusion switch, perform the sampling of the primary and secondary fusion value of the distribution network at the starting sampling speed, and transmit the sampled primary and secondary fusion value of the distribution network to the upper computer;

[0103] The evaluation module is used for the host computer to extract attributes of the primary and secondary fusion values ​​of the distribution network after sampling them, and to analyze the extracted attributes, and to estimate the change status of the primary and secondary fusion values ​​of the distribution network through the deep learning model of the analyzed attributes, and to perform an overall evaluation on the change status of the primary and secondary fusion values ​​of the distribution network;

[0104] The cutting module is used to cut the fusion value changes into different modes according to the estimated values, including reasonable change conditions and rapid change conditions;

[0105] The control module is used to face the changes in the fusion value under reasonable changes. It uses the initial sampling speed to perform the first and second fusion value sampling of the distribution network. If the measurement unit confirms that the fusion value change of the switch is in a rapid change state, the initial sampling speed is used as a condition to perform flexible control on the specific sampling speed.

[0106] The beneficial effects of the present invention are that, compared with the prior art, the technical effects of the present invention include:

[0107] It can achieve flexible and active sampling speed configuration, effectively improving the measurement sensitivity and timeliness of abnormal fluctuations in the integrated value. Especially when the integrated value of the switch shows rapid changes or hidden abnormalities, the measurement unit can actively improve the sampling speed to ensure the real-time grasp of important integrated values ​​and reduce the risk of delayed measurement. This kind of real-time speed control not only improves the early detection rate of switch faults, but also provides more accurate fault sampling for high-risk switches, which is convenient for early maintenance, thereby reducing the risk of switch damage or accidents, and ultimately significantly improving the reliability of the switch and the efficiency of switch fault control.

[0108] The present disclosure can be a system, method and / or computer program product. The computer program product can include a computer-readable backup medium carrying computer-readable program instructions for causing a processor to implement various aspects of the disclosure.

[0109] The computer readable backup medium can be a tangible network capable of retaining and backing up the instructions used by the instruction execution network. The computer readable backup medium can be, but is not limited to, an electrical backup network, a magnetic backup network, an optical backup network, an electromagnetic backup network, a semiconductor backup network, or any suitable combination of the above. Further examples of computer readable backup media (non-exhaustive list) include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disk read-only memory (HD-ROM), digital versatile disk (DXD), memory stick, floppy disk, mechanically encoded network, such as punch cards or protrusions in grooves with instructions backed up thereon, and any suitable combination of the above. The computer readable backup medium used herein is not to be construed as a transient signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., a light pulse through a power line cable), or an electrical signal transmitted through wires.

[0110] The computer readable program instructions expressed herein can be downloaded from the computer readable backup medium to each inference / processing power grid line, or downloaded to an external computer or external backup power grid line through a wireless network, such as the Internet, a local area network, a wide area network and / or a wireless network. The wireless network can include copper transmission cables, power transmission lines, wireless transmission, routers, firewalls, switches, gateway computers and / or edge service devices. The wireless network adapter card or wireless network interface in each inference / processing power grid line receives the computer readable program instructions from the wireless network and forwards the computer readable program instructions for storage in the computer readable backup medium in each inference / processing power grid line.

[0111] The computer program instructions for performing the operations of the present disclosure can be assembler instructions, instruction set architecture (ISA) instructions, machine instructions, machine-related instructions, microcode, firmware instructions, conditional setting values, or source code or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Sdaletal A, H++, etc., and conventional procedural programming languages ​​such as "H" language or similar programming languages. The computer-readable program instructions can be executed completely on the client computer, partially on the client computer, as a separate software package, partially on the client computer and partially on the remote computer, or completely on the remote computer or server. In the case of a remote computer, the remote computer can be connected to the client computer through any other wireless network, including a local area network (LAb) or a wide area network (WAb), or can be connected to an external computer (just like using an Internet service provider to connect through the Internet). In some embodiments, the electronic circuit is customized by using the status values ​​of computer-readable program instructions, such as a programmable logic circuit, a field programmable gate array (FPGA) or a programmable logic array (PLA), and the electronic circuit can execute computer-readable program instructions to achieve various aspects of the overhead disclosure.

[0112] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents, and any modifications or equivalent replacements that do not deviate from the spirit and scope of the present invention should be covered within the protection scope of the claims of the present invention.

Claims

1. A primary and secondary integration coordination method for a power distribution network of a power system, characterized in that: include: The measuring unit samples the voltage and current values ​​of the primary and secondary fusion switches in the distribution network and transmits them to the main controller. The main controller transmits the collected voltage and current values ​​of the primary and secondary fusion switches in the distribution network to the host computer for display and analysis. The voltage or current value of the primary and secondary fusion switch in the distribution network is the primary and secondary fusion value of the distribution network. The method in which the main controller transmits the collected voltage and current values ​​of the primary and secondary fusion switches in the distribution network to the upper computer for analysis includes: Step 1: According to the requirements of sampling the fusion value under the reasonable operation condition of the primary and secondary fusion switch, define a starting sampling speed for the measurement unit, perform the sampling of the primary and secondary fusion value of the distribution network at the starting sampling speed, and transmit the sampled primary and secondary fusion value of the distribution network to the host computer; Step 2: After sampling the primary and secondary fusion values ​​of the distribution network, the host computer extracts attributes of the primary and secondary fusion values ​​of the distribution network, and parses the extracted attributes. The analyzed attributes are used to estimate the change status of the primary and secondary fusion values ​​of the distribution network through a deep learning model, and an overall evaluation is performed on the change status of the primary and secondary fusion values ​​of the distribution network; Step 3: Based on the estimated values, the integrated value changes are divided into different modes, including reasonable changes and rapid changes; Step 4: In the face of changes in the fusion value under reasonable changes, the initial sampling speed is used to perform the first and second fusion value sampling of the distribution network. If the measurement unit confirms that the fusion value change of the switch is in a rapid change state, the initial sampling speed is used as a condition to perform flexible control on the specific sampling speed.

2. The primary and secondary integration coordination method of the distribution network of the power system according to claim 1 is characterized in that: In step 1, a starting sampling speed is initially defined for the measuring unit. This speed is defined based on the requirements of the fusion value fluctuation under the reasonable operating conditions of the primary and secondary fusion switch. After the measuring unit is running, the primary and secondary fusion values ​​of the distribution network of the primary and secondary fusion switch are sampled in real time according to the pre-defined starting sampling speed. The primary and secondary fusion values ​​of the distribution network are then transmitted to the host computer via the main controller.

3. The primary and secondary integration coordination method of the distribution network of the power system according to claim 2 is characterized in that: In step 2, the value after attribute extraction includes the deviation amplitude of the current fusion value and the reasonable standard fusion value of the switch and the sudden change of the fusion value in a short period of time. After obtaining the value after attribute extraction, during the measured time period, the deviation amplitude of the current fusion value and the reasonable standard fusion value of the switch and the sudden change of the fusion value in a short period of time are analyzed to form the fusion value deviation parameter and the sudden change fusion value parameter respectively, and send the fusion value deviation parameter and the sudden change fusion value parameter to the deep learning model after pre-learning, and form the fusion value dynamic change parameter through the deep learning model, and perform an overall evaluation on the change of the primary and secondary fusion values ​​of the distribution network through the fusion value dynamic change parameter.

4. The primary and secondary integration coordination method of the distribution network of the power system according to claim 3 is characterized in that: In step 2, the deep learning model after prior learning is a method model that has been constructed and improved through learning of past values ​​and corresponding attributes. The deep learning model after prior learning receives the input fusion value bias parameter and the suddenly changed fusion value parameter, and forms the fusion value dynamic change parameter; In step 2, the learning methods include: First, a number of past primary and secondary integrated values ​​of the distribution network are obtained as past values. The number of past primary and secondary integrated values ​​of the distribution network include integrated value change properties under various different conditions, including reasonable standard integrated values ​​and sudden change integrated values ​​during sudden changes. Then, the attribute extraction is performed on the primary and secondary fusion values ​​of several past distribution networks. The fusion value deviation parameters and the sudden change fusion value parameters after attribute extraction are used as the attributes of the input model, and the Gaussian mixture model is used to input the past values ​​into the model for learning; The final model is stored and used in real-time analysis. When new distribution network primary and secondary fusion values ​​are input, the model is estimated or grouped according to the previously learned model.

5. The primary and secondary integration coordination method of the distribution network of the power system according to claim 4 is characterized in that: In step 2, in a predefined measurement period, the method of analyzing the deviation amplitude of the current fusion value and the switch reasonable standard fusion value to form the fusion value deviation parameter includes: During the measurement period, the current distribution network primary and secondary fusion value IS of the switch is initially sampled. dvssfou , I.S. dvssfou Defined as the fusion value representing the current sampling, synchronous, and reasonable standard fusion value IS of the switch cbtfmjpf , I.S. cbtfmjpf Defined as the standard fusion value that represents the reasonable condition of the switch; Calculate the fusion value deviation between the current fusion value and the standard fusion value; Compute the fusion value bias parameter.

6. The primary and secondary integration coordination method of the distribution network of the power system according to claim 5 is characterized in that: The equation for calculating the fusion value bias parameter is: ISEJ υ =ΔIS*U x , in the equation, ISEJ υ Characterizes the bias parameter of the fusion value.

7. The primary and secondary integration coordination method of the power distribution network of the power system according to claim 6 is characterized in that: In step 2, during the measured period, the method of analyzing the sudden change of the fusion value of the switch in a short period of time to form a sudden change fusion value parameter includes: During the measurement period, the fusion value change level is calculated for each pair of continuous primary and secondary fusion value points of the distribution network. The calculation equation of the fusion value change level is: In the equation, H j Represents the level of change of the fusion value at time j, IS j With IS j+1 Respectively represent the fusion value at time j and j+1, Δu j Characterizes the size of the time period between time j and j+1; In the measured period, after calculating the fusion value changes at each moment through the hierarchy, the instantaneous total function of the change is calculated. The calculation equation is: D j represents the total function value at time j, H l represents the level of change of the fusion value calculated at time l, β represents the attenuation parameter, P represents the total number of numerical points in the measured time period, and e is the Euler number; The calculation equation for the sudden change in the fusion value parameter of the entire measurement period is: In the equation, ISTJ ν The fusion value parameter that characterizes the sudden change, D j represents the total function value at time j; The equation for calculating the deviation between the current fusion value and the standard fusion value is: ΔIS represents the deviation value of the enhanced fusion value. Import the criticality parameters of the time period and perform configuration according to the duration of the time period when the fusion value deviates continuously; Fusion value maneuvering variable parameter Ezpbnjd ifbsu The resulting operational equation is: In the equation, ζ1 and ζ2 are the fusion value bias parameters ISEJ υ ISTJ with the fusion value parameter of sudden change ν The predefined ratio parameter of , and ζ1, ζ2 are both above zero; The operation equation of the criticality parameter of the time period is: U x Characterize the criticality parameter of the time period, u efwjbujpq Characterizes the duration of the fusion value deviation, U xjoepx Characterizes the size of the time period being measured.

8. The primary and secondary integration coordination method of the power distribution network of the power system according to claim 7 is characterized in that: In step 3, the fusion value dynamic change parameter estimated by the deep learning model is compared and analyzed with the standard critical value of the fusion value dynamic change parameter defined in advance, and the fusion value change is divided into different modes, and the method includes: If the fusion value maneuvering change parameter is not lower than the fusion value maneuvering change parameter standard critical value, the fusion value change in the measured time period is cut into a rapid change state; If the fusion value maneuvering change parameter is lower than the standard critical value of the fusion value maneuvering change parameter, the fusion value change within the measured time period is cut into reasonable change conditions.

9. The primary and secondary integration coordination method of the power distribution network of the power system according to claim 8 is characterized in that: In step 4, in the face of the change of the fusion value under the rapidly changing condition, the initial sampling speed is used as a condition to perform a dynamic control on the specific sampling speed, and the method includes: According to the fusion value, the variable parameter Ezpbnjd is automatically changed ifbsu and fusion value maneuvering variable parameter standard critical value θ Ezpbnjd The relationship between them is used to calculate the control parameters. The calculation equation is: S represents the control parameter, which is used to configure the specific sampling speed, η represents the configuration parameter, and χ represents the gain parameter; After obtaining the control parameter S, the sampling speed multiplier is calculated. The calculation equation is: Δg represents the sampling speed multiplier, that is, the value to be increased on the initial sampling speed, g0 represents the initial sampling speed, and ξ represents the importance parameter; According to the calculated sampling speed multiplier, calculate the specific sampling speed. The calculation equation is: g bduvbm =g0*Δg, in the equation, g bduvbm Characterize the specific sampling speed after manipulation; The measuring unit configures the sampling speed to a specific sampling speed via an initial sampling speed, and performs sampling on the primary and secondary fusion values ​​of the switch's distribution network at the specific sampling speed.

10. A primary and secondary fusion coordination mode of a power distribution network of a power system, characterized in that: include: The online measuring machine is wirelessly connected to the host computer. The measuring unit in the online measuring machine is connected to the main controller. The measuring unit is used to sample the voltage and current values ​​of the primary and secondary fusion switches in the distribution network and transmit them to the main controller. The main controller is used to transmit the collected voltage and current values ​​of the primary and secondary fusion switches in the distribution network to the host computer for display and analysis. The voltage or current value of the primary and secondary fusion switch in the distribution network is the primary and secondary fusion value of the distribution network. The modules running on the host computer include: A definition module is used to define a starting sampling speed for the measurement unit according to the requirements of sampling the fusion value under the reasonable operation condition of the primary and secondary fusion switch, perform the sampling of the primary and secondary fusion value of the distribution network at the starting sampling speed, and transmit the sampled primary and secondary fusion value of the distribution network to the upper computer; The evaluation module is used for the host computer to extract attributes of the primary and secondary fusion values ​​of the distribution network after sampling them, and to analyze the extracted attributes, and to estimate the change status of the primary and secondary fusion values ​​of the distribution network through the deep learning model of the analyzed attributes, and to perform an overall evaluation on the change status of the primary and secondary fusion values ​​of the distribution network; The cutting module is used to cut the fusion value changes into different modes according to the estimated values, including reasonable change conditions and rapid change conditions; The control module is used to face the changes in the fusion value under reasonable changes. It uses the initial sampling speed to perform the first and second fusion value sampling of the distribution network. If the measurement unit confirms that the fusion value change of the switch is in a rapid change state, the initial sampling speed is used as a condition to perform flexible control on the specific sampling speed.

Images