Intrinsic safety monitoring system and method for branch cable of combiner box

Abstract

The invention discloses an intrinsic safety monitoring system and method for branch cables of a combiner box, and the system is characterized in that a temperature sensor network is internally provided with a plurality of temperature sensors, and the temperature sensors are at least used for detecting the cable temperature data of each branch cable in the combiner box; a plurality of data acquisition devices are arranged in the distributed data acquisition device and are used for acquiring cable temperature data of each branch cable in a preset area; the data processing module preprocesses the cable temperature data; the temperature prediction module generates a corresponding temperature prediction result; the alarm module generates corresponding alarm information; and the navigation module generates corresponding navigation information. Potential faults can be found in the initial stage of heating through the temperature sensor, and the timeliness of fault detection is improved.

Description

Technical Field

[0001] The present application relates to the field of Internet, and in particular to a system and method for intrinsic safety monitoring of branch cables in a combiner box. Background Art

[0002] Combiner box branch cables are used to connect combiner boxes with various photovoltaic modules or other power generation units in power systems such as photovoltaic power generation systems. Most of the faults during use (such as poor contact of crimping points, insulation aging, overload, short circuit, etc.) are often accompanied by heat. For more serious heat, it may even cause serious accidents such as fire.

[0003] However, in actual applications, the combiner box often contains a large number of branch cables, especially some large power stations, which also contain multiple combiner boxes, which further increases the number of branch cables and increases the difficulty of supervision.

[0004] In traditional monitoring solutions, cameras are usually used to capture images of the combiner box, and abnormal phenomena such as sparks and combustion in the images are analyzed to determine whether the combiner box is faulty.

[0005] However, usually only after a certain period of continuous heating will abnormal phenomena such as sparks and combustion occur. At this time, the junction box has already failed and has lasted for a long time. This makes this detection method have a lag and it is difficult to detect the failure of the junction box in time. Summary of the invention

[0006] In order to solve the above problems, the present application proposes an intrinsic safety monitoring system for a combiner box branch cable, comprising: a temperature sensor network, a distributed data acquisition device, and a monitoring center;

[0007] The temperature sensor network is provided with a plurality of temperature sensors, and the temperature sensors are at least used to detect the cable temperature data of each branch cable in the combiner box;

[0008] The distributed data acquisition device is provided with a plurality of data acquisition devices, and the data acquisition devices are connected to the temperature sensor network and are used to collect the cable temperature data of each branch cable in the preset area;

[0009] The monitoring center includes a data processing module, a temperature prediction module, an alarm module, and a navigation module;

[0010] The data processing module receives the cable temperature data fed back by the distributed data acquisition device, and pre-processes the cable temperature data;

[0011] The temperature prediction module performs prediction based on the cable temperature data to generate a corresponding temperature prediction result;

[0012] The alarm module makes an abnormality determination based on the cable temperature data and the temperature prediction result, and generates corresponding alarm information;

[0013] The navigation module generates corresponding navigation information according to the abnormal target location information contained in the warning information and the location information of the person who receives the warning information.

[0014] In one example, a plurality of sub-networks are provided in the temperature sensor network, and each sub-network corresponds to a single preset area;

[0015] Each sub-network includes at least one first temperature sensor and a plurality of second temperature sensors;

[0016] The distance between the first temperature sensor and the combiner box is less than a first preset distance, and is used to detect the ambient temperature data corresponding to the combiner box;

[0017] For the same branch cable, the second temperature sensors are respectively arranged at different positions of the branch cable, and are used to detect the cable temperature data corresponding to the combiner box.

[0018] In one example, for each branch cable in the temperature sensor network, a connection position between the branch cable and the combiner box is determined;

[0019] A second temperature sensor is arranged within a second preset distance of the connection position, for collecting temperature data of the first cable, and at least one second temperature sensor is arranged outside a third preset distance of the connection position, for collecting temperature data of the second cable at its own position;

[0020] The data processing module pre-processes and classifies the cable temperature data in each preset area;

[0021] According to the classification result, for a single branch cable, determine the number of branches of the branch cable currently detected by the second temperature sensor corresponding to the first cable temperature data, and determine the number of historical abnormalities at the location corresponding to each second cable temperature data;

[0022] When the alarm module makes an abnormality determination based on the temperature data, the first abnormality determination threshold of the first cable temperature data is adjusted according to the number of branches, and the second abnormality determination threshold of the second cable temperature data is adjusted according to the number of historical abnormalities;

[0023] The more the number of branches is, the higher the first abnormality determination threshold is; the more the number of historical abnormalities is, the lower the second abnormality determination threshold is.

[0024] In one example, the temperature prediction module generates a corresponding temperature prediction result for each cable temperature data;

[0025] The alarm module performs abnormality determination on each cable temperature data according to the temperature prediction result;

[0026] Determine a third temperature sensor corresponding to the abnormal cable temperature data, and determine other temperature sensors within an influence range corresponding to the third temperature sensor;

[0027] Taking the abnormal target position information corresponding to the third temperature sensor as the primary alarm target, and taking the abnormal target position information corresponding to other temperature sensors within the influence range as secondary alarm targets, and generating corresponding alarm information;

[0028] Among them, for the second temperature sensor set within the second preset distance of the connection position, its influence range includes the junction box where it is located and the corresponding one or more branch cables; for the second temperature sensor set outside the third preset distance of the connection position, its influence range includes the corresponding one or more branch cables.

[0029] In one example, the temperature prediction module performs prediction based on the cable temperature data and the ambient temperature data through a pre-trained regression model to generate a temperature prediction result corresponding to the second temperature sensor.

[0030] In one example, the training process of the regression model includes:

[0031] Generate a corresponding time period according to the ambient temperature data;

[0032] During the time period, the corresponding cable temperature data is collected by the second temperature sensor to form a corresponding time series, and the time series is processed for stability;

[0033] Performing autocorrelation analysis and partial autocorrelation analysis on the time series, and selecting a regression model with a matching architecture according to the analysis results; wherein the architecture of the regression model includes: an autoregressive model, a moving average model, an autoregressive moving average model, and an autoregressive integrated moving average model;

[0034] According to the selected regression model, model parameters are estimated according to the analysis results, and fitting is performed according to the estimated model parameters;

[0035] The fitting results are evaluated, and the regression model is optimized according to the evaluation results.

[0036] In one example, the temperature prediction module determines an upstream device to which the branch cable is connected, and determines a device type and a device status of the upstream device;

[0037] According to the device type and the device status, modifying the temperature prediction result of the first cable temperature data;

[0038] The process of correction includes:

[0039] According to the equipment type, selecting power generation equipment from the upstream equipment, and determining the equipment quantity and power generation type of the power generation equipment;

[0040] If the number of the equipment is single, a first correction coefficient corresponding to the power generation equipment is determined according to a first preset coefficient corresponding to the power generation type and a difference between the equipment state and a preset normal state, and the temperature prediction result of the first cable temperature data is corrected by the first correction coefficient;

[0041] If the number of the devices is at least two, then for each power generation device, determine a first correction coefficient corresponding to the first correction coefficient;

[0042] If there are multiple power generation types in all power generation equipment, for each power generation equipment, the first correction coefficient of the power generation equipment is adjusted according to the number of power generation types to obtain a second correction coefficient, and the temperature prediction result of the first cable temperature data is corrected by the second correction coefficient;

[0043] The correction degree of the second correction coefficient is higher than that of the first correction coefficient.

[0044] In one example, the navigation module abstracts the map of the current area into a spatial map;

[0045] Generate corresponding nodes and edges in the spatial graph; wherein the nodes include primary nodes and secondary nodes, corresponding to the primary warning target and the secondary warning target respectively, and the edges correspond to roads in the current area;

[0046] Generate a corresponding personnel node in the spatial graph according to the personnel location information;

[0047] For each node, calculating the shortest spatial distance between the node and other nodes in the spatial graph;

[0048] Taking the personnel node as the starting point and the main node as the end point, generating a first navigation path according to the corresponding shortest spatial distance;

[0049] The personnel node is used as the starting point, the main node is used as the end point, and one or more secondary nodes are used as path nodes by arranging and combining the shortest spatial distances between the nodes, and the corresponding second navigation paths are generated respectively;

[0050] Among all the second navigation paths, the second navigation paths whose spatial distance is greater than the spatial distance corresponding to the first navigation path by more than a fourth preset distance are deleted, and among the remaining second navigation paths, the second navigation path with the largest number of passing nodes is selected as the third navigation path;

[0051] Generate corresponding navigation information according to the first navigation path and the third navigation path.

[0052] In one example, the system further includes: a cloud platform;

[0053] The cloud platform is used to back up and record at least one of the cable temperature data, the temperature prediction result, the abnormality determination result, the alarm information, and the navigation information.

[0054] On the other hand, the present application also proposes a method for intrinsically monitoring safety of a combiner box branch cable, wherein safety monitoring is performed by using an intrinsically monitoring safety system for a combiner box branch cable as described in any of the above examples, and the method includes:

[0055] The cable temperature data of each branch cable in the combiner box is detected by using multiple temperature sensors in the temperature sensor network;

[0056] The cable temperature data is collected by multiple data collection devices arranged in the distributed data collection device, and transmitted to the monitoring center;

[0057] Preprocessing the cable temperature data through a data processing module in the monitoring center, and predicting the cable temperature data through a temperature prediction module in the monitoring center to generate a corresponding temperature prediction result;

[0058] An alarm module in the monitoring center makes an abnormality determination based on the cable temperature data and the temperature prediction result, and generates corresponding alarm information;

[0059] The corresponding navigation information is generated by a navigation module in the monitoring center according to the abnormal target location information contained in the alarm information and the location information of the personnel who receive the alarm information.

[0060] The intrinsic safety monitoring system for combiner box branch cables proposed in this application can bring the following benefits:

[0061] Beneficial effects:

[0062] 1. Compared with detecting sparks and combustion to determine faults, this application can directly monitor the temperature of the junction box branch cable in real time through the temperature sensor network, and detect potential faults at the early stage of heating through the temperature sensor, thereby improving the timeliness of fault detection. In addition, by predicting the temperature change trend of the branch cable through the temperature prediction module, it is possible to further detect possible abnormal temperature increases in advance, warn of possible faults in advance, notify maintenance personnel in advance, and reduce the probability of faults.

[0063] 2. The temperature sensor network is distributed on each branch cable, which can accurately determine which branch cable has an abnormal temperature, and the branch cable positioning method is more accurate. In the complex situation of large power stations with many branch cables and junction boxes, the faulty cable can be quickly located, reducing the scope and time of troubleshooting and improving maintenance efficiency.

[0064] 3. The maintenance process is optimized through the navigation module. After the location of the faulty cable is determined, the navigation module can provide maintenance personnel with accurate navigation information to help them quickly reach the fault site. In large power stations or complex wiring environments, it can effectively save maintenance personnel time in finding the fault point and improve the efficiency of the entire maintenance work.

[0065] 4. The distributed data acquisition device can effectively collect the data from each temperature sensor and transmit it to the monitoring center. In the monitoring center, the data processing module can uniformly store, organize and analyze the data, thereby realizing remote monitoring and management of the combiner box. BRIEF DESCRIPTION OF THE DRAWINGS

[0066] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0067] Figure 1 This is a schematic diagram of the architecture of the intrinsic safety monitoring system for the combiner box branch cables in an embodiment of the present application;

[0068] Figure 2 Schematic diagram of the training process of the regression model in the embodiment of the present application;

[0069] Figure 3 A schematic diagram of generating a navigation path in an embodiment of the present application;

[0070] Figure 4 It is a flow chart of the intrinsic safety monitoring method for the combiner box branch cables in the embodiment of the present application. DETAILED DESCRIPTION

[0071] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0072] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0073] like Figure 1 As shown, an embodiment of the present application provides an intrinsic safety monitoring system for branch cables of a combiner box: a temperature sensor network, a distributed data acquisition device, and a monitoring center.

[0074] The temperature sensor network is provided with multiple temperature sensors, which can be used to detect different temperature data of the combiner box, branch cables, different locations, environments, etc. according to their different locations. Of course, the temperature sensor is used to detect the cable temperature data of each branch cable in the combiner box at least.

[0075] The temperature sensor network uses industrial-grade digital temperature sensors (for example, DS18B20 or PT100), and the sensor housing is made of high-temperature resistant flame-retardant materials with a protection level of IP67 or above. It is fixed to the measured part by a snap-on clamp or thermal tape. Each temperature sensor has a built-in unique ID code, and the coding rule adopts a three-level structure of "preset area number-device type-serial number". For example, A01-JH-001 represents the A01 area environmental monitoring type No. 1 sensor.

[0076] Specifically, in some large power stations, there are multiple junction boxes, each of which includes multiple branch cables. Each branch cable itself also has a certain length, so multiple sub-networks are set in the temperature sensor network, and each sub-network corresponds to a single preset area (for example, the area where each junction box is located, or the area where multiple adjacent junction boxes are located is taken as a single preset area, or the division principles can be further set, including: branch cables of the same electrical circuit are classified into the same sub-network, adjacent junction boxes with a distance of less than 5 meters are classified as the same sub-network, and the coverage area of ​​each sub-network is less than 100 square meters, etc.), each sub-network is equipped with a Zigbee self-organizing network module, and the network topology adopts a star + mesh hybrid structure. By gridding the temperature sensor network, it can be more convenient to manage the temperature sensor network.

[0077] Each sub-network includes at least one first temperature sensor and a plurality of second temperature sensors. It should be noted that both the first temperature sensor and the second temperature sensor are temperature sensors, and the different descriptions are made here only for the convenience of description.

[0078] The distance between the first temperature sensor and the junction box is lower than the first preset distance (for example, it can be 30cm±5cm), which is used to detect the ambient temperature data corresponding to the junction box. Of course, the installation position of the temperature sensor should avoid the heat dissipation channel of the box body and be higher than 10cm from the nearest heat dissipation hole to make the detection more accurate. If a single preset area contains multiple junction boxes, the ambient temperature data detected by the first temperature sensor can be directly used as the ambient temperature data corresponding to each of the multiple junction boxes.

[0079] Generally speaking, the temperature of the branch cable at the combiner box is likely to reach a higher temperature, so only a first temperature sensor needs to be set at the combiner box to detect the ambient temperature data. For other positions of the branch cable, the ambient temperature data can be directly used as its own ambient temperature data.

[0080] In addition, each branch cable has a certain length, so for the same branch cable, the second temperature sensor is set at different positions of the branch cable to detect the cable temperature data corresponding to the junction box. The setting position can be set at a fixed distance interval (for example, the fixed distance interval is about 10% of the cable length, and the minimum interval is higher than 1 meter), or it can be set according to actual conditions (for example, set at a location prone to failure).

[0081] Of course, if the distance between multiple branch cables is very close (for example, when the cable spacing is less than 15cm), a second temperature sensor can also be used to simultaneously detect the cable temperature data of multiple branch cables at their corresponding positions. In this case, a multi-probe temperature sensor can be used, each probe corresponds to a cable, and the probe spacing can be adjusted.

[0082] Furthermore, when setting the second temperature sensor, since the connection position between the branch cable and the combiner box is usually a fault-prone location and its temperature is likely to be higher, the connection position between the branch cable and the combiner box is determined for each branch cable in the temperature sensor network.

[0083] A second temperature sensor is set within a second preset distance of the connection position (determined according to the volume of the junction box, for example, 20cm±5cm) (contact temperature measurement can be used in this case, and the sensor probe is in direct contact with the copper core conductor of the cable, which can collect the temperature more accurately) to collect the temperature data of the first cable. At least one second temperature sensor is set outside a third preset distance of the connection position (determined according to the length of the branch cable, for example, at least 1 meter) (the setting position can be a fault-prone position determined in historical records, or a related position can be set at a fixed distance interval) to collect the temperature data of the second cable at its own position (non-contact infrared temperature measurement can be used in this case to detect the cable skin temperature for easy position adjustment).

[0084] A plurality of data acquisition devices are arranged in the distributed data acquisition device, and the data acquisition devices are connected to the temperature sensor network and are used to collect the cable temperature data of each branch cable in the preset area.

[0085] Among them, the sampling frequency of the data acquisition device is 1Hz~1kHz and is adjustable, the input channel is 16 differential inputs, the ADC resolution is 24 bits, the communication interfaces include RS485, Ethernet, 4G wireless, etc., the operating temperature is -40℃~85℃, and it can also be equipped with a signal conditioning circuit, which includes low-pass filtering (cut-off frequency 100Hz), programmable amplification (gain 1~1000 times adjustable), cold-end compensation (for thermocouples) and other modules.

[0086] Generally speaking, each preset area corresponds to a data acquisition device, which is used to collect the cable temperature data collected by the temperature sensor in the area. However, in some relatively large preset areas, multiple data acquisition devices can also be set.

[0087] Each data acquisition device has multiple data acquisition channels, using time division multiplexing technology. Each channel supports up to 256 sensors for polling acquisition, and the polling cycle is configurable. In this way, each data acquisition channel can be used to collect data from a single temperature sensor in the same time period.

[0088] The monitoring center communicates with the data acquisition device to obtain corresponding cable temperature data and perform corresponding data processing.

[0089] Specifically, the monitoring center includes a data processing module, a temperature prediction module, an alarm module, and a navigation module.

[0090] The data processing module receives the cable temperature data fed back by the distributed data acquisition device and pre-processes the cable temperature data.

[0091] Specifically, the data processing module preprocesses the cable temperature data in each preset area and classifies them. Preprocessing can include conventional preprocessing (for example, data cleaning, format conversion, etc.) and custom preprocessing (setting corresponding processing rules according to the actual scenario). Classification refers to determining the preset area to which each temperature sensor belongs, whether the first cable temperature data or the second cable temperature data collected, etc., based on the unique identifier of each temperature sensor. Data cleaning can include: outlier removal (using the 3σ criterion, marking as abnormal when 3 consecutive sampling points exceed the mean ±3 times the standard deviation), missing value compensation (using linear interpolation to compensate for less than 5 consecutive missing points), and noise filtering (using sliding average filtering, which is adjustable in window width of 5 to 15 points).

[0092] The temperature prediction module predicts the cable temperature data and generates corresponding temperature prediction results.

[0093] The temperature prediction module predicts the cable temperature data and the ambient temperature data through a pre-trained regression model, and generates a temperature prediction result corresponding to the second temperature sensor, so as to predict and warn the cable temperature in advance.

[0094] Specifically, Figure 2 As shown in Figure 1, the training process of the regression model includes:

[0095] After the original data is input, the corresponding time period is generated according to the ambient temperature data. That is, seasonal analysis is first performed, by drawing a line graph of the ambient temperature data or using the seasonal decomposition method to observe whether the data has seasonal patterns. If there are seasonal patterns, the corresponding time period is determined (usually the seasonal cycle is the standard seasonal cycle, for example, the seasonality with a one-year cycle has a cycle of 12 months, the seasonality with a one-week cycle has a cycle of 7 days, etc.).

[0096] During the time period, the corresponding cable temperature data is collected by the second temperature sensor to form a corresponding time series, in which the corresponding temperature value can be collected and recorded every preset time (usually in the range of several seconds to more than ten seconds) to form a sequence. The sequence can be stored in the form of a collection or a line graph.

[0097] Perform stationarity processing on the time series. Generally speaking, the regression model requires the data to be stationary, so the time series data is first tested for stationarity, for example, using a unit root test (such as an ADF test) to determine whether the time series has a unit root. If a unit root exists, it means that the data is non-stationary.

[0098] For non-stationary time series, you can perform a difference operation to make it stationary. Among them, the first-order difference can usually eliminate the trend of the data and calculate the difference between the data at adjacent time points. If it is still not stationary after the first-order difference, you can also perform a second-order or higher-order difference. At the same time, you can also observe the autocorrelation function (ACF) and partial autocorrelation function (PACF) of the data after the difference to determine whether the stationarity of the data meets the requirements.

[0099] Then, autocorrelation analysis and partial autocorrelation analysis can be performed on the time series, and a regression model with a matching architecture can be selected based on the analysis results. The architecture of the regression model includes: autoregressive model, moving average model, and autoregressive moving average model.

[0100] Specifically, the autocorrelation function (ACF) can reflect the correlation between the time series and its lagged values, while the partial autocorrelation function (PACF) measures the direct correlation between the time series and its lagged values ​​after controlling the influence of the intermediate terms.

[0101] Therefore, you can select the regression model of the corresponding architecture by observing the graphs of ACF and PACF.

[0102] If the autocorrelation function (ACF) shows tails and the partial autocorrelation function (PACF) is truncated after a certain lag order (such as p), the autoregressive model AR(p) model can be selected. The autoregressive model AR(p) model assumes that the current value is a linear combination of the past p values ​​plus a white noise term. For example, the form of the AR(1) model is where y t The temperature value at time t (that is, the temperature value corresponding to the cable temperature data), is the autoregressive coefficient, ∈ t is white noise. The autoregressive model is suitable for describing situations where the current temperature value is mainly affected by its past value. Among them, white noise is a random process, and the white noise sequence is a sequence with a mean of zero, a constant variance, and each value in the sequence is independent of each other. If the residual of the model is white noise, it means that the model has successfully extracted all the useful information in the data and there are no remaining predictable patterns. If the residual is not white noise, for example, there is autocorrelation in the residual, it means that the model may not have fully captured the dynamic laws in the data, and there is some information that can be used to further improve the model.

[0103] If the ACF is truncated after a certain lag order (for example, qth order) and the PACF is tailing, the moving average model MA(q) model can be selected. The MA(q) model assumes that the current value is a linear combination of the past q white noise terms plus a constant and the current white noise term. For example, the MA(1) model can be written as t =μ+θ1∈t-1 +∈ t , where μ is a constant and θ1 is the moving average coefficient. The moving average model is suitable for situations where temperature changes are mainly affected by past random shocks (white noise).

[0104] If both ACF and PACF show tailing, you can choose the autoregressive moving average model ARMA model to fit. The ARMA model combines the characteristics of autoregressive and moving average. The autoregressive moving average model ARMA (p, q) model can be written as It is applicable to complex situations where temperature changes are affected by both their own past values ​​and past random shocks.

[0105] If the original temperature data is non-stationary and becomes stationary data after differencing, and the ACF and PACF of the data after differentiation show the characteristics of the above-mentioned AR model, MA model or ARMA model, then the autoregressive integrated moving average model ARIMA model can be used. The d in the autoregressive integrated moving average model ARIMA(p,d,q) model represents the order of differentiation, which is used to process non-stationary data so that the data can meet the assumptions of the AR model, MA model or ARMA model after differentiation. For example, if the original data meets the characteristics of ARMA(p,q) after the first-order difference, then the corresponding ARIMA model is ARIMA(p,1,q). Generally speaking, the ARIMA(p,d,q) model can be written as Where B is the backshift operator, and By is defined t =y t-1 , B 2 y t =y t-2 , and so on. in, is the autoregressive coefficient, and p is the autoregressive order, which represents the autoregressive relationship between the current value and the past p values. (1-B) d is the difference operator, d is the difference order. θ(B)=1+θ1B+θ2B 2 +…+θ q B q is the polynomial of the moving average part, θ1…θ q is the moving average coefficient, q is the moving average order, which represents the moving average relationship between the current value and the past q white noise items. ∈ t is a white noise sequence.

[0106] After selecting the corresponding regression model, the model parameters are estimated according to the analysis results based on the selected regression model, and fitting is performed based on the estimated model parameters.

[0107] Taking the autoregressive moving average model as an example, we can find the maximum lag order at which the PACF and ACF values ​​are significantly different from zero based on the PACF and ACF graphs, preliminarily determine the values ​​of p and q, and then adjust the values ​​of p and q, try different values, and finally determine the size of the p and q values ​​by combining the model's fitting effect and statistical indicators. The value of d can be determined by the previous difference operation. The value of d is determined by the number of orders of difference after which the data reaches stability.

[0108] For the regression model, after the initial values ​​of the model parameters are determined, fitting is performed using methods such as least squares or maximum likelihood estimation. During the fitting process, the regression model will estimate the parameter values ​​of the regression model based on the data in the given time series, so that the regression model can best describe the changing pattern of the data.

[0109] The fitting results are evaluated and the regression model is optimized based on the evaluation results.

[0110] Among them, the evaluation indicators may include: mean square error (MSE), mean absolute error (MAE), mean absolute percentage error (MAPE), etc. MSE measures the average of the square of the error between the predicted value and the actual value, MAE is the average of the absolute error between the predicted value and the actual value, and MAPE is the average of the absolute percentage error. The smaller the values ​​of these indicators, the better the prediction effect of the model.

[0111] You can also analyze the residuals of the model to check whether they meet the characteristics of white noise, that is, whether the residuals have a mean of zero, a variance of constant, and no autocorrelation. If the residuals do not meet the characteristics of white noise, it means that the model may not capture information or may have overfitting problems, and the model needs to be further adjusted.

[0112] When optimizing the model, if the prediction effect of the model is not ideal, you can try to adjust the values ​​of model parameters such as p, d, q, refit the model, or consider other transformations of the data (such as logarithmic transformation, Box-Cox transformation, etc.) to improve the characteristics of the data and improve the fitting effect of the model. Alternatively, you can change the model architecture and retrain to obtain a regression model.

[0113] Taking the SARIMA model as an example, the periodic parameter s=24 (corresponding to a 24-hour daily period) can be added and implemented using the Python statsmodels library. The model update strategy uses a sliding window mechanism, and the model is retrained every time 1,000 new data points are added.

[0114] The alarm module makes an abnormality judgment based on the cable temperature data and temperature prediction results, and generates corresponding alarm information. Among them, if the cable temperature data or temperature prediction results exceed the preset normal value, it is considered to be abnormal and an alarm information should be generated. The alarm information may include the alarm target (select which maintenance personnel to alarm, for example, determined according to the day's duty, determined according to the person in charge of each junction box, determined according to the current distance of each person, etc.), the alarm method (which method to choose for the alarm, such as social software messages, text messages, phone calls, emails, etc.), the alarm level (for example, a three-level alarm mechanism is adopted, the first level alarm (yellow): the temperature exceeds the threshold by 10%, the second level alarm (orange): the temperature exceeds the threshold by 20% or is predicted to exceed the threshold within 1 hour, the third level alarm (red): the temperature exceeds the threshold by 30% or is predicted to exceed the threshold within 30 minutes), etc.

[0115] Furthermore, after the temperature prediction module generates a corresponding temperature prediction result for each cable temperature data, the alarm module performs an abnormality determination on each cable temperature data according to the temperature prediction result.

[0116] At this time, the third temperature sensor corresponding to the abnormal cable temperature data (that is, the temperature sensor corresponding to the abnormal cable temperature data) is determined, and other temperature sensors within the influence range corresponding to the third temperature sensor are determined.

[0117] Among them, the impact range is pre-set. For example, for the second temperature sensor set within the second preset distance of the connection position, since it monitors the connection position, if an impact occurs, it usually affects the entire branch cable. Therefore, the impact range includes the junction box where it is located and the corresponding one or more branch cables (wherein, the number of corresponding branch cables depends on how many branch cables the second temperature sensor monitors at the same time). For the second temperature sensor set outside the third preset distance of the connection position, its impact range is relatively limited, and only targets the corresponding branch cable itself, that is, its impact range includes the corresponding one or more branch cables (similarly, it depends on how many branch cables the second temperature sensor monitors at the same time).

[0118] At this time, the abnormal target position information corresponding to the third temperature sensor can be considered as the location where the abnormality is likely to occur, and this location is used as the primary alarm target. The abnormal target position information corresponding to other temperature sensors within the impact range is considered as the location that may be affected, and this location is used as the secondary alarm target to generate corresponding alarm information.

[0119] The navigation module generates corresponding navigation information according to the abnormal target location information contained in the alarm information and the location information of the person receiving the alarm information.

[0120] Specifically, when the personnel location information is outside the park where the combiner box is located, the navigation information can be divided into two parts. The part outside the park can be navigated by integrating the corresponding third-party program, and for the part inside the park, since the third-party map often does not have a comprehensive and detailed understanding, it is completed by itself.

[0121] First, the map of the current area is abstracted into a spatial map. Generally speaking, for most parks, a two-dimensional spatial map is sufficient, while for parks with more complex height information (for example, the terrain is more complex, or the junction box is built on a high-rise building), a corresponding three-dimensional spatial map needs to be set.

[0122] Then, the corresponding nodes and edges are generated in the spatial graph. The nodes include primary nodes and secondary nodes, which correspond to the primary warning targets and secondary warning targets respectively, and the edges correspond to the roads in the current area. Of course, if the warning information only contains the primary warning target, the secondary nodes can be no longer generated.

[0123] At the same time, a corresponding personnel node is generated in the spatial graph according to the personnel location information. If the maintenance personnel enters from outside the park, the location of the entrance door can be used as the personnel location information. If the maintenance personnel is currently in the park, the current location information of the maintenance personnel can be obtained according to the positioning device of the smart terminal worn by the maintenance personnel as the personnel location information.

[0124] For each node, calculate the shortest spatial distance between the node and other nodes in the spatial graph. The shortest spatial distance is not the straight-line distance, but the distance that can be reached through edge connection. Each node can be used as the starting point, and the distance of all paths from the node to other nodes can be traversed to finally determine the shortest spatial distance.

[0125] Then, the personnel node is used as the starting point and the main node is used as the end point, and a first navigation path is generated according to the corresponding shortest spatial distance. The first navigation path includes the corresponding shortest spatial distance and the corresponding navigation route, and may also include recommended transportation methods (including walking, cycling, driving, etc.) according to the terrain.

[0126] At the same time, in addition to the first navigation path, in order to enable the maintenance personnel to contact as many secondary nodes as possible on the way to the main node without wasting time, the personnel node can be used as the starting point and the main node as the end point. By arranging and combining the shortest spatial distance between the nodes, one or more secondary nodes can be used as the way nodes to generate corresponding second navigation paths respectively.

[0127] For example, Figure 3As shown, assuming that the current personnel node is node A, the main node is node B, and there are two secondary nodes, namely node C and node D, then the permutations and combinations are performed to generate multiple second navigation paths, and the distance between each two nodes in the second navigation path is the shortest spatial distance between the two nodes. At this time, the second navigation path includes: ACB, ADB, ACDB, ADCB.

[0128] In order to prevent the maintenance personnel from being delayed in going to the main node due to the distance being too far, the second navigation paths whose spatial distance is higher than the spatial distance corresponding to the first navigation path by more than a fourth preset distance are deleted from all the second navigation paths. Figure 3 For example, after calculation, assuming that the distances of the routes of ADCB and ACDB do not meet the requirements, they are deleted.

[0129] At the same time, in the remaining second navigation path (at this time, Figure 3 In the example of ACB and ADB, in order to allow maintenance personnel to see the status of as many secondary nodes as possible, so that they can quickly determine the status of the primary nodes and perform advance maintenance on the secondary nodes, the second navigation path with the largest number of nodes can be selected as the third navigation path. Figure 3 In the example of , since the number of path nodes in all the remaining second navigation paths is the same, ACB with the shortest distance can be selected as the third navigation path.

[0130] According to the first navigation path (in Figure 3 The third navigation path (indicated by a solid line in Figure 3 The navigation information contains both navigation paths, which can be selected by maintenance personnel. According to different actual situations, they can decide whether to go directly to the main node or go to the secondary node first.

[0131] The intrinsic safety monitoring system for combiner box branch cables proposed in this application can bring the following benefits:

[0132] Beneficial effects:

[0133] 1. Compared with detecting sparks and combustion to determine faults, this application can directly monitor the temperature of the junction box branch cable in real time through the temperature sensor network, and detect potential faults at the early stage of heating through the temperature sensor, thereby improving the timeliness of fault detection. In addition, by predicting the temperature change trend of the branch cable through the temperature prediction module, it is possible to further detect possible abnormal temperature increases in advance, warn of possible faults in advance, notify maintenance personnel in advance, and reduce the probability of faults.

[0134] 2. The temperature sensor network is distributed on each branch cable, which can accurately determine which branch cable has an abnormal temperature, and the branch cable positioning method is more accurate. In the complex situation of large power stations with many branch cables and junction boxes, the faulty cable can be quickly located, reducing the scope and time of troubleshooting and improving maintenance efficiency.

[0135] 3. The maintenance process is optimized through the navigation module. After the location of the faulty cable is determined, the navigation module can provide maintenance personnel with accurate navigation information to help them quickly reach the fault site. In large power stations or complex wiring environments, it can effectively save maintenance personnel time in finding the fault point and improve the efficiency of the entire maintenance work.

[0136] 4. The distributed data acquisition device can effectively collect the data from each temperature sensor and transmit it to the monitoring center. In the monitoring center, the data processing module can uniformly store, organize and analyze the data, thereby realizing remote monitoring and management of the combiner box.

[0137] In one embodiment, the data processing module can also determine, based on the classification results, for a single branch cable, the number of branches of the branch cable currently detected by the second temperature sensor corresponding to the first cable temperature data. For example, at the connection position in the junction box, since the distance between the multiple branch cables at the connection position is very close, a second temperature sensor is used to simultaneously detect the first cable temperature of four branch cables. At this time, the number of branches of the branch cable corresponding to the first cable temperature is four. At the same time, the number of historical abnormalities at the position corresponding to each second cable temperature data is determined. This data can be obtained from the corresponding historical database. The number of historical abnormalities (for example, temperature abnormalities) near the position corresponding to the second cable temperature data can all be used as the corresponding number of historical abnormalities.

[0138] At this time, when the alarm module makes an abnormality judgment based on the temperature data, it can adjust the first abnormality judgment threshold of the first cable temperature data according to the number of branches, and adjust the second abnormality judgment threshold of the second cable temperature data according to the number of historical abnormalities.

[0139] The more branches there are, the more upstream devices they are connected to. Even when the connection position is working normally, the temperature will be higher. Therefore, the higher the first abnormality judgment threshold, the higher the judgment standard can be. The more historical abnormalities there are, the greater the probability of abnormalities occurring at the subsequent locations of the branch cable. Therefore, the lower the second abnormality judgment threshold, the stricter the requirement is to detect whether the branch cable has abnormalities at this location.

[0140] In one embodiment, if the temperature prediction module can also consider the impact of upstream equipment when performing temperature prediction, the accuracy of the temperature prediction result will be further improved.

[0141] Specifically, the temperature prediction module determines the upstream device connected to the branch cable, and determines the device type and device status of the upstream device. Each branch cable is connected to an upstream device, and all branch cables in a junction box may be connected to the same or different upstream devices. Equipment types mainly include power generation equipment and power storage equipment, and for power generation equipment, more detailed equipment types can be set, such as wind power generation equipment, hydropower generation equipment, etc. As for the equipment status of power generation equipment, it can be divided into high load state, normal state, low load state, etc. according to the load conditions.

[0142] At this time, according to the device type and device status, the temperature prediction result of the first cable temperature data (which corresponds to the cable temperature data collected by the second temperature sensor set within the second preset distance of the connection position) is corrected, so that the temperature prediction result is more accurate. Here, only the temperature prediction result of the first cable temperature data is corrected because only the cable temperature data near the connection position is more susceptible to the influence of the upstream device.

[0143] The process of correction includes:

[0144] First, according to the equipment type, select the power generation equipment from the upstream equipment, and determine the equipment quantity and power generation type of the power generation equipment.

[0145] If the number of devices is single, it means that the current junction box is connected to the same power generation device. At this time, the first correction coefficient corresponding to the power generation device is determined according to the first preset coefficient corresponding to the power generation type and the gap between the device state and the preset normal state. For example, the ratio between the device state and the preset normal state is calculated. The ratio represents the gap between the power generation device and the normal state. Then, the gap is reduced or enlarged by a reasonable value through the first preset coefficient to generate the first correction coefficient. The temperature prediction result of the first cable temperature data is corrected by the first correction coefficient. Generally speaking, the greater the gap between the device state and the preset normal state, the greater the upward correction degree of the temperature prediction result. If the device state has not reached the preset normal state, no correction is required.

[0146] If the number of devices is at least two, a first correction coefficient corresponding to each power generation device is determined.

[0147] If there are multiple power generation types in all power generation equipment, there may be incompatibility in the power generation results of the multiple power generation types, which may cause more serious heat generation. Therefore, for each power generation equipment, the first correction coefficient of the power generation equipment is adjusted according to the number of power generation types (generally speaking, the more the number of power generation types, the higher the degree of adjustment of the first correction coefficient) to obtain the second correction coefficient. At this time, the correction degree of the second correction coefficient obtained after adjustment is higher than that of the first correction coefficient, which corresponds to the possible incompatibility that will aggravate the heat generation.

[0148] The temperature prediction result of the first cable temperature data is corrected by the second correction coefficient. Since there are multiple power generation equipment, each power generation equipment has its own second correction coefficient. Assuming that at this time, the branch cable corresponding to each power generation equipment is the first cable temperature data collected by an independent temperature sensor, then each first cable temperature data can be corrected independently. If the first cable temperature data of multiple branch cables are collected by the same temperature sensor, the first cable temperature data is a unified value and is used for these multiple branch cables at the same time. Then, the largest second correction coefficient can be selected from all power generation equipment to correct the unified first cable temperature data.

[0149] In one embodiment, Figure 1 As shown, the system further includes: a cloud platform. The cloud platform is used to back up and record at least one of the cable temperature data, temperature prediction results, abnormality determination results, alarm information, and navigation information, so as to facilitate tracing.

[0150] like Figure 4 As shown, the embodiment of the present application further provides a method for intrinsically monitoring safety of a combiner box branch cable, wherein safety monitoring is performed by using an intrinsically monitoring safety system for a combiner box branch cable as described in any of the above embodiments, and the method includes:

[0151] S401: Detecting cable temperature data of each branch cable in a combiner box through a plurality of temperature sensors in a temperature sensor network.

[0152] S402: The cable temperature data is collected by using a plurality of data collection devices in the distributed data collection device, and the data is transmitted to a monitoring center.

[0153] S403: pre-processing the cable temperature data through a data processing module in the monitoring center, and predicting based on the cable temperature data through a temperature prediction module in the monitoring center to generate a corresponding temperature prediction result.

[0154] S404: An alarm module in the monitoring center performs abnormality determination based on the cable temperature data and the temperature prediction result, and generates corresponding alarm information.

[0155] S405: Generate corresponding navigation information through a navigation module in the monitoring center according to the abnormal target location information contained in the alarm information and the location information of the person who receives the alarm information.

[0156] The above is only the embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the present application.

Claims

1. An intrinsic safety monitoring system for combiner box branch cables, characterized in that: include: Temperature sensor network, distributed data acquisition device, monitoring center; The temperature sensor network is provided with a plurality of temperature sensors, and the temperature sensors are at least used to detect the cable temperature data of each branch cable in the combiner box; The distributed data acquisition device is provided with a plurality of data acquisition devices, and the data acquisition devices are connected to the temperature sensor network and are used to collect the cable temperature data of each branch cable in the preset area; The monitoring center includes a data processing module, a temperature prediction module, an alarm module, and a navigation module; The data processing module receives the cable temperature data fed back by the distributed data acquisition device, and pre-processes the cable temperature data; The temperature prediction module performs prediction based on the cable temperature data to generate a corresponding temperature prediction result; The alarm module makes an abnormality determination based on the cable temperature data and the temperature prediction result, and generates corresponding alarm information; The navigation module generates corresponding navigation information according to the abnormal target location information contained in the warning information and the location information of the person who receives the warning information.

2. The system according to claim 1, characterized in that The temperature sensor network is provided with a plurality of sub-networks, each sub-network corresponding to a single preset area; Each sub-network includes at least one first temperature sensor and a plurality of second temperature sensors; The distance between the first temperature sensor and the combiner box is less than a first preset distance, and is used to detect the ambient temperature data corresponding to the combiner box; For the same branch cable, the second temperature sensors are respectively arranged at different positions of the branch cable, and are used to detect the cable temperature data corresponding to the combiner box.

3. The system according to claim 2, characterized in that For each branch cable in the temperature sensor network, determining a connection position between the branch cable and the combiner box; A second temperature sensor is arranged within a second preset distance of the connection position, for collecting temperature data of the first cable, and at least one second temperature sensor is arranged outside a third preset distance of the connection position, for collecting temperature data of the second cable at its own position; The data processing module pre-processes and classifies the cable temperature data in each preset area; According to the classification result, for a single branch cable, determine the number of branches of the branch cable currently detected by the second temperature sensor corresponding to the first cable temperature data, and determine the number of historical abnormalities at the location corresponding to each second cable temperature data; When the alarm module makes an abnormality determination based on the temperature data, the first abnormality determination threshold of the first cable temperature data is adjusted according to the number of branches, and the second abnormality determination threshold of the second cable temperature data is adjusted according to the number of historical abnormalities; The more the number of branches is, the higher the first abnormality determination threshold is; the more the number of historical abnormalities is, the lower the second abnormality determination threshold is.

4. The system according to claim 3, characterized in that The temperature prediction module generates a corresponding temperature prediction result for each cable temperature data; The alarm module performs abnormality determination on each cable temperature data according to the temperature prediction result; Determine a third temperature sensor corresponding to the abnormal cable temperature data, and determine other temperature sensors within an influence range corresponding to the third temperature sensor; Taking the abnormal target position information corresponding to the third temperature sensor as the primary alarm target, and taking the abnormal target position information corresponding to other temperature sensors within the influence range as secondary alarm targets, and generating corresponding alarm information; Among them, for the second temperature sensor set within the second preset distance of the connection position, its influence range includes the junction box where it is located and the corresponding one or more branch cables; for the second temperature sensor set outside the third preset distance of the connection position, its influence range includes the corresponding one or more branch cables.

5. The system according to claim 2, characterized in that The temperature prediction module performs prediction based on the cable temperature data and the ambient temperature data through a pre-trained regression model to generate a temperature prediction result corresponding to the second temperature sensor.

6. The system according to claim 5, characterized in that The training process of the regression model includes: Generate a corresponding time period according to the ambient temperature data; During the time period, the corresponding cable temperature data is collected by the second temperature sensor to form a corresponding time series, and the time series is processed for stability; Performing autocorrelation analysis and partial autocorrelation analysis on the time series, and selecting a regression model with a matching architecture according to the analysis results; wherein the architecture of the regression model includes: an autoregressive model, a moving average model, an autoregressive moving average model, and an autoregressive integrated moving average model; According to the selected regression model, model parameters are estimated according to the analysis results, and fitting is performed according to the estimated model parameters; The fitting results are evaluated, and the regression model is optimized according to the evaluation results.

7. The system according to claim 3, characterized in that The temperature prediction module determines the upstream device to which the branch cable is connected, and determines the device type and device status of the upstream device; According to the device type and the device status, modifying the temperature prediction result of the first cable temperature data; The process of correction includes: According to the equipment type, selecting power generation equipment from the upstream equipment, and determining the equipment quantity and power generation type of the power generation equipment; If the number of the equipment is single, a first correction coefficient corresponding to the power generation equipment is determined according to a first preset coefficient corresponding to the power generation type and a difference between the equipment state and a preset normal state, and the temperature prediction result of the first cable temperature data is corrected by the first correction coefficient; If the number of the devices is at least two, then for each power generation device, determine a first correction coefficient corresponding to the first correction coefficient; If there are multiple power generation types in all power generation equipment, for each power generation equipment, the first correction coefficient of the power generation equipment is adjusted according to the number of power generation types to obtain a second correction coefficient, and the temperature prediction result of the first cable temperature data is corrected by the second correction coefficient; The correction degree of the second correction coefficient is higher than that of the first correction coefficient.

8. The system according to claim 4, characterized in that The navigation module abstracts the map of the current area into a spatial map; Generate corresponding nodes and edges in the spatial graph; wherein the nodes include primary nodes and secondary nodes, corresponding to the primary warning target and the secondary warning target respectively, and the edges correspond to roads in the current area; Generate a corresponding personnel node in the spatial graph according to the personnel location information; For each node, calculating the shortest spatial distance between the node and other nodes in the spatial graph; Taking the personnel node as the starting point and the main node as the end point, generating a first navigation path according to the corresponding shortest spatial distance; The personnel node is used as the starting point, the main node is used as the end point, and one or more secondary nodes are used as path nodes by arranging and combining the shortest spatial distances between the nodes, and the corresponding second navigation paths are generated respectively; Among all the second navigation paths, the second navigation paths whose spatial distance is greater than the spatial distance corresponding to the first navigation path by more than a fourth preset distance are deleted, and among the remaining second navigation paths, the second navigation path with the largest number of passing nodes is selected as the third navigation path; Generate corresponding navigation information according to the first navigation path and the third navigation path.

9. The system according to claim 1, characterized in that The system also includes: a cloud platform; The cloud platform is used to back up and record at least one of the cable temperature data, the temperature prediction result, the abnormality determination result, the alarm information, and the navigation information.

10. A method for intrinsic safety monitoring of branch cables in a combiner box, characterized in that: The safety monitoring is performed by the intrinsic safety monitoring system for the combiner box branch cable according to any one of claims 1 to 9, and the method comprises: The cable temperature data of each branch cable in the combiner box is detected by using multiple temperature sensors in the temperature sensor network; The cable temperature data is collected by using a plurality of data collection devices arranged in a distributed data collection device, and transmitted to a monitoring center; Preprocessing the cable temperature data through a data processing module in the monitoring center, and predicting the cable temperature data through a temperature prediction module in the monitoring center to generate a corresponding temperature prediction result; An alarm module in the monitoring center makes an abnormality determination based on the cable temperature data and the temperature prediction result, and generates corresponding alarm information; The corresponding navigation information is generated by a navigation module in the monitoring center according to the abnormal target location information contained in the alarm information and the location information of the personnel who receive the alarm information.

Images