Multi-inductive-head wireless communication management and control method and system based on water leakage prevention controller

Abstract

The invention discloses a multi-inductive-head wireless communication management and control method and system based on a water leakage prevention controller, and the method comprises the steps: obtaining the construction information of a storage device, extracting the construction characteristics of the storage device, analyzing a leaky region of the storage device, and formulating a leakage inductive head module placement scheme and a water leakage prevention controller scheme of a target storage device; setting a wireless communication rule between the inductive head modules and the water leakage prevention controller, acquiring monitoring data of the plurality of associated multi-inductive head modules at a preset acquisition frequency based on the data acquisition rule, and performing data collision detection and management and control; monitoring the storage state of the target storage device to obtain storage device monitoring information, analyzing whether leakage occurs or not and the leakage degree, and performing early warning prompt and leakage control; and constructing an energy condition sensing model based on the generative adversarial network, monitoring real-time energy consumption of the multi-inductive-head module, analyzing whether energy consumption abnormity exists, and performing maintenance prompting. And the accuracy and intelligence of water leakage monitoring are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of water leakage prevention equipment control, and in particular to a multi-sensor head wireless communication control method and system based on a water leakage prevention controller. Background Art

[0002] With the growing demand for intelligent monitoring, multi-sensor head monitoring scenarios have gradually become the mainstream application model. Although the wired communication method widely used in existing water leakage monitoring systems can ensure the stability of signal transmission, it is complex in wiring and has high installation and maintenance costs. Especially in large-scale monitoring scenarios, it cannot flexibly respond to complex deployment requirements.

[0003] In addition, although wireless monitoring technology has solved the wiring problem to a certain extent, in the multi-sensor head scenario, due to the lack of an effective communication control mechanism, there are often problems such as data transmission conflicts, serious signal interference, and excessive delays, resulting in water leakage events not being captured and processed in a timely manner. At the same time, the operating status of the sensor head and controller is not monitored in real time, and equipment failure or insufficient battery power may cause the system's monitoring capabilities to decline, thereby affecting the reliability and real-time nature of water leakage warnings. Summary of the invention

[0004] The present invention overcomes the defects of the prior art and provides a multi-sensor head wireless communication control method and system based on a water leakage prevention controller, an important purpose of which is to improve the accuracy and intelligence of water leakage monitoring.

[0005] To achieve the above objectives, the first aspect of the present invention provides a multi-sensor head wireless communication control method based on a water leakage prevention controller, comprising:

[0006] Obtain the storage device structure information of the target area, extract the storage device structure characteristics to analyze the leakage-prone areas of the storage device, and formulate the leakage sensor head module placement plan and anti-leakage controller plan for the target storage device;

[0007] Set the wireless communication rules between the sensor head module and the water leakage prevention controller, obtain the monitoring data of several associated multi-sensor head modules at a preset collection frequency based on the data collection rules, and perform data collision detection and control;

[0008] Monitor the storage status of the target storage device to obtain storage device monitoring information, analyze whether there is a leak and the extent of the leak, and provide early warning prompts and leak control;

[0009] An energy status perception model is built based on a generative adversarial network to monitor the real-time energy consumption of the multi-sensing head module, analyze whether there is any energy consumption abnormality, and provide maintenance prompts.

[0010] In this solution, the extraction of storage device structural features to analyze the leak-prone areas of the storage device and the formulation of a leakage sensing head module placement plan and a water leakage prevention controller for the target storage device specifically include:

[0011] Acquire storage device construction information of a target area, perform feature extraction on the storage device construction information, and obtain storage device construction feature information, wherein the storage device construction feature information includes storage device structure features and storage device material features;

[0012] Through data retrieval, water leakage instances of target storage devices with several storage specifications are obtained, features are extracted from each historical instance, and the extracted features are classified into categories based on the storage specifications to construct an instance data set;

[0013] Based on the cosine metric algorithm, the storage device structural feature information is matched and analyzed with the feature data in the instance data set, and the leak-prone area of ​​the target storage device is analyzed to obtain leak-prone area analysis information;

[0014] According to the leak-prone area analysis information, the historical leakage frequency of the corresponding area is obtained through the instance data set as a priority indicator, and the priority of each leak-prone area is defined to obtain priority analysis information;

[0015] A leakage sensing head module placement plan for the target storage device is formulated in combination with the leakage-prone area analysis information and the priority analysis information, the leakage sensing head module is placed in the target storage device, and a water leakage prevention controller is set based on the actual monitoring area and the priority of the placement area.

[0016] In this solution, the wireless communication rules between the sensor head module and the anti-leakage controller are set, and the monitoring data of several associated multi-sensor head modules are obtained at a preset collection frequency based on the data collection rules, and data collision detection and control are performed, specifically including:

[0017] Based on the TDMA mechanism, a fixed data transmission time slot is allocated to each sensor head module, and the LoRa protocol is used to set the wireless communication rules between the sensor head module and the anti-leakage controller;

[0018] The data collection rules of the water leakage prevention controller are set. The water leakage prevention controller obtains the monitoring data of several associated multi-sensing head modules at a preset collection frequency based on the data collection rules, and performs data collision detection;

[0019] By sending a test command to each multi-sensing head module to obtain a feedback signal, it is determined whether a collision occurs based on the obtained feedback signal. If the number of data packets received per unit time is greater than a preset threshold, it indicates that a collision occurs;

[0020] Obtain the conflict data of the collision and perform feature extraction, extract the identification features of the conflict data, take the minimum average response time as the optimization goal, introduce the PSO algorithm to use the identification features of the conflict data to initialize the particle swarm, and iterate the analysis to obtain the first analysis information;

[0021] A collision control strategy is generated based on the first analysis information to control the multiple sensor head modules within the jurisdiction.

[0022] In this solution, the storage status of the target storage device is monitored to obtain storage device monitoring information, analyze whether leakage occurs and the extent of leakage, and provide early warning prompts and leakage control, specifically including:

[0023] Based on data retrieval, historical monitoring data of the multi-sensor head module under different leakage degrees are obtained to form a first data set, leakage degree categories are defined and the corresponding historical monitoring data are associated, and monitoring data features of each leakage degree category are extracted according to the association results;

[0024] A leakage perception model is constructed based on the noise reduction autoencoder structure, Gaussian noise is added to the extracted monitoring data features of each leakage degree category, and feature encoding is performed using a multi-layer perceptron.

[0025] The encoded monitoring data feature data is input into the LSTM network for time series feature extraction, the extracted time series features are decoded and dimensionally upgraded, and then input into the leakage perception model for iterative training until a leakage perception model that meets the expectations is obtained;

[0026] The storage status of the target storage device is monitored by arranging a plurality of multi-sensing head modules, storage device monitoring information is acquired, and data preprocessing is performed on the storage device monitoring information to obtain preprocessing information;

[0027] Preset a timestamp, perform time series processing on the preprocessed information according to the timestamp to generate a time series sequence, input the sequence into the leakage perception model for analysis, and obtain leakage perception analysis information;

[0028] Based on the leakage perception analysis information, it is determined whether the target storage device has a leakage risk, and a leakage warning report is generated to indicate the area and extent of the leakage. The corresponding leakage control strategy is obtained to generate a control instruction and send it to the water leakage prevention controller for control.

[0029] In this solution, the energy status perception model is constructed based on the generative adversarial network to monitor the real-time energy consumption of the multi-sensing head module, analyze whether there is energy consumption abnormality, and provide maintenance prompts, specifically including:

[0030] Acquire normal energy consumption data when the multi-sensing head module monitors the target storage device, preset a unit time step, and process the acquired normal energy consumption data into sequence data separated by the preset unit time step;

[0031] The energy consumption data corresponding to each unit time step is taken as a state vector, and each state vector is subjected to dimensionality reduction processing, and a state vector matrix after dimensionality reduction is constructed. The Markov algorithm is used to calculate the probability value of each state vector in the state vector matrix transferring to another state vector;

[0032] An energy status perception model is built based on a generative adversarial network. The state transition matrix is ​​generated through the calculated state transition probability to characterize the transition relationship between each state vector. The training data set is combined with the corresponding normal energy consumption data to train the energy status perception model.

[0033] Acquire real-time energy consumption monitoring information when the multi-sensing head module monitors the target storage device, perform time series processing on the real-time energy consumption monitoring information, and input the processed time series sequence into the energy status perception model;

[0034] The input real-time energy consumption monitoring data sequence is taken as the original sequence, the state transfer matrix is ​​obtained and the generator is used to generate a reconstructed sequence, the reconstructed sequence is input into the discriminator to determine whether to accept the current reconstructed sequence, and iterative generation and judgment are performed to obtain the final reconstructed sequence.

[0035] In this solution, the energy status perception model is constructed based on the generative adversarial network to monitor the real-time energy consumption of the multi-sensing head module, and analyze whether there is an abnormal energy consumption, and provide maintenance prompts, and also includes:

[0036] Generate a predicted value of energy consumption of the multi-sensing head module under normal conditions according to the final reconstruction sequence, and calculate a reconstruction error according to the final reconstruction sequence and the original sequence;

[0037] Acquire real-time energy consumption monitoring information, calculate the predicted value of energy consumption of the multi-sensing head module under normal conditions and the real-time energy consumption monitoring information, and obtain the deviation between the predicted value and the actual value;

[0038] Performing average filtering on the calculated deviation values, generating a deviation time series curve based on the filtered deviation values ​​according to the time series characteristics, and performing fitting based on the calculated reconstruction errors to generate a reconstruction error time series curve;

[0039] Performing dynamic time warping on the deviation timing curve and the reconstruction error timing curve based on a dynamic warping algorithm, and calculating an average dynamic time warping distance between the deviation timing curve and the reconstruction error timing curve;

[0040] A preset distance threshold is set. When the average dynamic time warping distance is greater than the preset distance threshold, it indicates that there is an abnormal energy consumption condition. Then the source data corresponding to the current deviation timing curve is marked as abnormal data for source tracing analysis.

[0041] Based on the traceability analysis results, abnormal energy consumption warning information is generated, indicating that the corresponding multi-sensor head module has an abnormality and needs to be repaired.

[0042] The second aspect of the present invention provides a multi-sensor head wireless communication control system based on a water leakage prevention controller, the system comprising: a memory, a processor, the memory containing a multi-sensor head wireless communication control method program based on a water leakage prevention controller, the multi-sensor head wireless communication control method program based on a water leakage prevention controller is executed by the processor to implement the following steps:

[0043] Obtain the storage device structure information of the target area, extract the storage device structure characteristics to analyze the leakage-prone areas of the storage device, and formulate the leakage sensor head module placement plan and anti-leakage controller plan for the target storage device;

[0044] Set the wireless communication rules between the sensor head module and the water leakage prevention controller, obtain the monitoring data of several associated multi-sensor head modules at a preset collection frequency based on the data collection rules, and perform data collision detection and control;

[0045] Monitor the storage status of the target storage device to obtain storage device monitoring information, analyze whether there is a leak and the extent of the leak, and provide early warning prompts and leak control;

[0046] An energy status perception model is built based on a generative adversarial network to monitor the real-time energy consumption of the multi-sensing head module, analyze whether there is any energy consumption abnormality, and provide maintenance prompts.

[0047] The present invention discloses a multi-sensor head wireless communication control method and system based on a water leakage prevention controller, including: obtaining storage device structural information, extracting storage device structural features to analyze the leak-prone areas of the storage device, and formulating a leakage sensing head module placement plan and a water leakage prevention controller plan for the target storage device; setting wireless communication rules between the sensing head module and the water leakage prevention controller, obtaining monitoring data of several associated multi-sensor head modules at a preset acquisition frequency based on the data acquisition rules, and performing data collision detection and control; monitoring the storage status of the target storage device to obtain storage device monitoring information, analyzing whether leakage occurs and the degree of leakage, and performing early warning prompts and leakage control; constructing an energy status perception model based on a generative adversarial network, monitoring the real-time energy consumption of the multi-sensor head module, analyzing whether there is energy consumption abnormality, and providing maintenance prompts. The accuracy and intelligence of water leakage monitoring are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments or exemplary embodiments of the present invention, the drawings required for use in the embodiments or exemplary descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained according to the drawings without paying creative work.

[0049] Figure 1 A flow chart of a multi-sensor head wireless communication control method based on a water leakage prevention controller provided in one embodiment of the present invention;

[0050] Figure 2 A flow chart of an energy consumption monitoring method applied to a multi-sensing head module provided by an embodiment of the present invention;

[0051] Figure 3 A block diagram of a multi-sensor head wireless communication control system based on a water leakage prevention controller provided by an embodiment of the present invention;

[0052] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0053] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0054] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0055] Figure 1 A flow chart of a multi-sensor head wireless communication control method based on a water leakage prevention controller provided in one embodiment of the present invention;

[0056] like Figure 1 As shown, the present invention provides a flow chart of a multi-sensor head wireless communication control method based on a water leakage prevention controller, including:

[0057] S102, obtaining storage device structure information of the target area, extracting storage device structure features to analyze the leak-prone areas of the storage devices, and formulating a leakage sensing head module placement plan and a water leakage prevention controller plan for the target storage devices;

[0058] S104, setting a wireless communication rule between the sensing head module and the water leakage prevention controller, acquiring monitoring data of a plurality of associated sensing head modules at a preset acquisition frequency based on the data acquisition rule, and performing data collision detection and control;

[0059] S106, monitoring the storage status of the target storage device to obtain storage device monitoring information, analyzing whether leakage occurs and the extent of leakage, and providing early warning prompts and leakage control;

[0060] S108, constructing an energy status perception model based on a generative adversarial network, monitoring the real-time energy consumption of the multi-sensing head module, and analyzing whether there is any abnormal energy consumption, and providing maintenance prompts.

[0061] It should be noted that the present invention provides a multi-sensor head wireless communication control method and system based on a water leakage prevention controller, which ensures accurate positioning of high-risk areas and identifies leak-prone areas of the equipment by analyzing the physical characteristics of the equipment structure and the statistical laws of historical leakage data. An optimized placement scheme for the leakage sensing head module of the target storage device is formulated to maximize the monitoring coverage. At the same time, a matching water leakage prevention controller scheme is designed to ensure that the system can respond quickly and take corresponding control measures when a leak is detected. Subsequently, clear communication protocols and rules are set to ensure the efficiency and reliability of data transmission. Based on the pre-established data acquisition rules, monitoring data is collected from multiple sensing head modules at a preset frequency and data collision detection and control are performed to avoid signal conflicts caused by multiple sensing heads sending data at the same time, thereby ensuring the integrity and real-time nature of the data. Further, a comprehensive analysis is performed on the storage status of the target storage device to determine whether there is a leak. If a leak is detected, the corresponding early warning prompts and leakage control measures are triggered according to the real-time situation, such as shutting down the water source in a specific area or starting the leakage treatment equipment. In addition, by monitoring the real-time energy consumption of the sensing head module, dynamic analysis is performed to determine whether there is abnormal energy consumption. For example, if the energy consumption of some sensor head modules is much higher than that of other modules, it may indicate that the equipment has failed or the environmental conditions have affected its normal operation. Through the energy anomaly analysis results, maintenance personnel are provided with maintenance tips to ensure the long-term stable operation of the entire monitoring system. It effectively improves the water leakage prevention ability and system reliability of the storage device.

[0062] Further, in a preferred embodiment of the present invention, the extraction of storage device structural features to analyze the leak-prone areas of the storage device, and the formulation of a leakage sensing head module placement plan and a water leakage prevention controller for the target storage device specifically include:

[0063] Acquire storage device construction information of a target area, perform feature extraction on the storage device construction information, and obtain storage device construction feature information, wherein the storage device construction feature information includes storage device structure features and storage device material features;

[0064] Through data retrieval, water leakage instances of target storage devices with several storage specifications are obtained, features are extracted from each historical instance, and the extracted features are classified into categories based on the storage specifications to construct an instance data set;

[0065] Based on the cosine metric algorithm, the storage device structural feature information is matched and analyzed with the feature data in the instance data set, and the leak-prone area of ​​the target storage device is analyzed to obtain leak-prone area analysis information;

[0066] According to the leak-prone area analysis information, the historical leakage frequency of the corresponding area is obtained through the instance data set as a priority indicator, and the priority of each leak-prone area is defined to obtain priority analysis information;

[0067] A leakage sensing head module placement plan for the target storage device is formulated in combination with the leakage-prone area analysis information and the priority analysis information, the leakage sensing head module is placed in the target storage device, and a water leakage prevention controller is set based on the actual monitoring area and the priority of the placement area.

[0068] It should be noted that, first, the construction information of the storage device is obtained and feature extraction is performed to generate the construction feature information of the storage device, including its structural features and material features. The structural features mainly describe the appearance, connection points and possible weak links of the device, while the material features include the type of material constituting the device, corrosion resistance and pressure resistance, etc. These features together reflect the potential leakage risk points of the device. Next, multiple historical leakage instances of target storage devices with similar storage specifications are collected through data retrieval means. After detailed feature extraction of these leakage instances, the extracted features are classified according to the storage specifications to form an instance data set. The structural feature information of the storage device is matched and analyzed with the feature data in the instance data set based on the cosine metric algorithm. The algorithm identifies the similar parts of the target storage device in terms of structure and material features with the leakage device in the historical instance by calculating the similarity between the features, and points out the specific areas in the device where leakage is most likely to occur. The historical leakage frequency of these areas is further extracted from the instance data set as a priority indicator. By analyzing and comparing the leakage frequency of each leaky area, the system defines priorities for these areas. For example, areas with higher leakage frequencies are given higher priorities. Finally, the leak sensor module placement plan for the target storage device is developed by combining the leak-prone area analysis information and the priority analysis information. In this plan, the sensor module is placed in the high-priority area first, and covers other leak-prone areas to achieve comprehensive monitoring. At the same time, the anti-leakage controller is set according to the actual monitoring area and area priority to achieve efficient management and analysis of the sensor module data, ensuring a quick response when a leak is detected.

[0069] Further, in a preferred embodiment of the present invention, the wireless communication rules between the sensor head module and the water leakage prevention controller are set, and the monitoring data of the associated multiple sensor head modules are obtained at a preset acquisition frequency based on the data acquisition rules, and data collision detection and control are performed, specifically including:

[0070] Based on the TDMA mechanism, a fixed data transmission time slot is allocated to each sensor head module, and the LoRa protocol is used to set the wireless communication rules between the sensor head module and the anti-leakage controller;

[0071] The data collection rules of the water leakage prevention controller are set. The water leakage prevention controller obtains the monitoring data of several associated multi-sensing head modules at a preset collection frequency based on the data collection rules, and performs data collision detection;

[0072] By sending a test command to each multi-sensing head module to obtain a feedback signal, it is determined whether a collision occurs based on the obtained feedback signal. If the number of data packets received per unit time is greater than a preset threshold, it indicates that a collision occurs;

[0073] Obtain the conflict data of the collision and perform feature extraction, extract the identification features of the conflict data, take the minimum average response time as the optimization goal, introduce the PSO algorithm to use the identification features of the conflict data to initialize the particle swarm, and iterate the analysis to obtain the first analysis information;

[0074] A collision control strategy is generated based on the first analysis information to control the multiple sensor head modules within the jurisdiction.

[0075] It should be noted that in order to achieve efficient wireless communication between multiple sensing head modules and the anti-leakage controller, a fixed data transmission time slot is allocated to each sensing head module based on the time division multiple access (TDMA) mechanism. The LoRa protocol is used to further set the communication rules between the sensing head module and the anti-leakage controller to ensure that the data can be stably transmitted in a low-power, long-distance wireless transmission environment. Avoid conflicts in communication resources and improve transmission efficiency and reliability. In terms of data acquisition, the anti-leakage controller obtains monitoring data from multiple sensing head modules at a preset frequency according to the set data acquisition rules. In this process, the controller performs collision detection on the received data to determine whether there is a situation where multiple sensing head modules send data in the same time slot. The anti-leakage controller sends test instructions to each sensing head module and receives feedback signals to analyze whether data collision occurs. If the number of data packets received per unit time exceeds the preset threshold, it is determined that a collision has occurred, indicating that multiple modules attempt to transmit data at the same time, resulting in a communication conflict. Then, the conflicting data that has collided is extracted and its characteristics are analyzed. The identification features of the conflicting data include key attributes such as the source information, timestamp, and conflict frequency of the data packet. In order to optimize the data transmission process, the particle swarm optimization (PSO) algorithm is introduced with the goal of minimizing the average response time. First, the particle swarm is initialized using the identification features of the conflicting data, and through multiple iterative analyses, the first analysis information is obtained to identify the optimal time slot allocation strategy to reduce the possibility of data collision. Based on the first analysis information, a collision control strategy is generated to dynamically adjust the working mode and communication time slot allocation of the multi-sensing head module. Effectively manage and control the sensing head modules within the jurisdiction to ensure that the transmission time of each module is in order during the data collection process. Improving the efficiency of wireless communication and optimizing the coordination ability of the sensing head modules provide technical guarantees for the precise monitoring of the anti-leakage controller.

[0076] Further, in a preferred embodiment of the present invention, the monitoring of the storage status of the target storage device to obtain storage device monitoring information, analyzing whether leakage occurs and the degree of leakage, and performing early warning prompts and leakage control specifically include:

[0077] Based on data retrieval, historical monitoring data of the multi-sensor head module under different leakage degrees are obtained to form a first data set, leakage degree categories are defined and the corresponding historical monitoring data are associated, and monitoring data features of each leakage degree category are extracted according to the association results;

[0078] A leakage perception model is constructed based on the noise reduction autoencoder structure, Gaussian noise is added to the extracted monitoring data features of each leakage degree category, and feature encoding is performed using a multi-layer perceptron.

[0079] The encoded monitoring data feature data is input into the LSTM network for time series feature extraction, the extracted time series features are decoded and dimensionally upgraded, and then input into the leakage perception model for iterative training until a leakage perception model that meets the expectations is obtained;

[0080] The storage status of the target storage device is monitored by arranging a plurality of multi-sensing head modules, storage device monitoring information is acquired, and data preprocessing is performed on the storage device monitoring information to obtain preprocessing information;

[0081] Preset a timestamp, perform time series processing on the preprocessed information according to the timestamp to generate a time series sequence, input the sequence into the leakage perception model for analysis, and obtain leakage perception analysis information;

[0082] Based on the leakage perception analysis information, it is determined whether the target storage device has a leakage risk, and a leakage warning report is generated to indicate the area and extent of the leakage. The corresponding leakage control strategy is obtained to generate a control instruction and send it to the water leakage prevention controller for control.

[0083] It should be noted that in order to comprehensively monitor and analyze the leakage risk of the target storage device, the historical monitoring data of the multi-sensor head module under different leakage degrees is first obtained through data retrieval, and multiple leakage degree categories are defined, such as slight leakage, moderate leakage and severe leakage, and the corresponding historical monitoring data is associated with these categories. By analyzing the association results, the monitoring data features of each leakage degree category are extracted. The leakage perception model is constructed using a noise reduction autoencoder structure. Gaussian noise is added to the extracted monitoring data features of each leakage degree category, and these features are encoded using a multi-layer perceptron to enhance the robustness of the model to data noise. Then, the encoded monitoring data features are input into the long short-term memory network (LSTM) to extract the time series features in the monitoring data. The LSTM network extracts deep features that reflect the dynamic changes of leakage by analyzing the time series change pattern of the data. After decoding and dimensionality upgrading these time series features, they are input into the leakage perception model for iterative training. Through multiple iterative optimizations, the model gradually converges to the desired performance level. Next, the storage status of the target storage device is monitored in real time through the deployment of several multi-sensing head modules, and the collected storage device monitoring information is preprocessed to remove outliers and redundant information to obtain more accurate information. The preprocessed information is time-series processed based on the preset timestamp to generate a data sequence with time series characteristics. It is input into the leakage perception model for analysis to generate leakage perception analysis information. Based on the leakage perception analysis information, the system determines whether there is a leakage risk in the target storage device. If a leakage risk is found, the specific area and severity of the leakage are further analyzed, and the corresponding leakage control strategy is obtained to generate control instructions, and the instructions are sent to the water leakage prevention controller, which then takes necessary protective measures, such as shutting off the relevant water source or starting remedial equipment.

[0084] Furthermore, in a preferred embodiment of the present invention, the energy status perception model is constructed based on the generative adversarial network to monitor the real-time energy consumption of the multi-sensing head module, and analyze whether there is abnormal energy consumption, and provide maintenance prompts, specifically including:

[0085] Acquire normal energy consumption data when the multi-sensing head module monitors the target storage device, preset a unit time step, and process the acquired normal energy consumption data into sequence data separated by the preset unit time step;

[0086] The energy consumption data corresponding to each unit time step is taken as a state vector, and each state vector is subjected to dimensionality reduction processing, and a state vector matrix after dimensionality reduction is constructed. The Markov algorithm is used to calculate the probability value of each state vector in the state vector matrix transferring to another state vector;

[0087] An energy status perception model is built based on a generative adversarial network. The state transition matrix is ​​generated through the calculated state transition probability to characterize the transition relationship between each state vector. The training data set is combined with the corresponding normal energy consumption data to train the energy status perception model.

[0088] Acquire real-time energy consumption monitoring information when the multi-sensing head module monitors the target storage device, perform time series processing on the real-time energy consumption monitoring information, and input the processed time series sequence into the energy status perception model;

[0089] The input real-time energy consumption monitoring data sequence is taken as the original sequence, the state transfer matrix is ​​obtained and the generator is used to generate a reconstructed sequence, the reconstructed sequence is input into the discriminator to determine whether to accept the current reconstructed sequence, and iterative generation and judgment are performed to obtain the final reconstructed sequence.

[0090] It should be noted that, first, the energy consumption data of the multi-sensing head module under normal working conditions is obtained. A fixed time step is preset, and the normal energy consumption data obtained is divided into sequence data separated by a preset unit time step. Each state vector is subjected to dimensionality reduction processing, and a state vector matrix is ​​formed according to the state vector after dimensionality reduction. The Markov algorithm is used to calculate the probability value of each state vector in the state vector matrix transferring to other state vectors. The state transfer matrix is ​​generated by these probability values, and the matrix represents the dynamic transfer relationship between different state vectors. Then, an energy status perception model is constructed based on a generative adversarial network (GAN). The generative adversarial network consists of a generator and a discriminator. The calculated state transfer matrix and the corresponding normal energy consumption data are used to generate a training data set, and the energy status perception model is trained with the data set. Through this process, the model can learn the time series characteristics of the normal energy consumption state and its changing rules. Then, the energy consumption monitoring information of the multi-sensing head module is obtained in real time, and the time series processing is performed on it, and it is input into the energy status perception model. The model uses the real-time data sequence as the original sequence and analyzes it in combination with the state transfer matrix learned in the training. The generator generates a reconstructed sequence based on the input state information, which is an approximate prediction of the original sequence. Subsequently, the reconstructed sequence is input to the discriminator, which determines whether to accept the current reconstruction result by comparing the original sequence and the reconstructed sequence. Through multiple iterations of generation and judgment, the final reconstructed sequence is obtained.

[0091] Furthermore, in a preferred embodiment of the present invention, the energy status perception model is constructed based on the generative adversarial network to monitor the real-time energy consumption of the multi-sensing head module, and analyze whether there is abnormal energy consumption, and provide maintenance prompts, and also includes:

[0092] Generate a predicted value of energy consumption of the multi-sensing head module under normal conditions according to the final reconstruction sequence, and calculate a reconstruction error according to the final reconstruction sequence and the original sequence;

[0093] Acquire real-time energy consumption monitoring information, calculate the predicted value of energy consumption of the multi-sensing head module under normal conditions and the real-time energy consumption monitoring information, and obtain the deviation between the predicted value and the actual value;

[0094] Performing average filtering on the calculated deviation values, generating a deviation time series curve based on the filtered deviation values ​​according to the time series characteristics, and performing fitting based on the calculated reconstruction errors to generate a reconstruction error time series curve;

[0095] Performing dynamic time warping on the deviation timing curve and the reconstruction error timing curve based on a dynamic warping algorithm, and calculating an average dynamic time warping distance between the deviation timing curve and the reconstruction error timing curve;

[0096] A preset distance threshold is set. When the average dynamic time warping distance is greater than the preset distance threshold, it indicates that there is an abnormal energy consumption condition. Then the source data corresponding to the current deviation timing curve is marked as abnormal data for source tracing analysis.

[0097] Based on the traceability analysis results, abnormal energy consumption warning information is generated, indicating that the corresponding multi-sensor head module has an abnormality and needs to be repaired.

[0098] It should be noted that after obtaining the final reconstruction sequence, it represents the predicted value of energy consumption of the multi-sensing head module under normal working conditions. By comparing the final reconstruction sequence with the original monitoring data, the reconstruction error is calculated, which reflects the deviation between the model prediction value and the actual monitoring value. Next, the real-time energy consumption monitoring information is obtained, and the predicted value of energy consumption under normal conditions is calculated with the real-time data to calculate the deviation between the predicted value and the actual value. The calculated deviation value is averaged and filtered to eliminate noise and smooth the data. The deviation time series curve is generated according to the time series characteristics of the filtered deviation value. At the same time, based on the calculated reconstruction error, a time series curve of the reconstruction error is generated to represent the error change between the prediction and the actual data. Next, based on the dynamic warping algorithm, the deviation time series curve and the reconstruction error time series curve are dynamically warped in time series, and the time axes of the two curves are adjusted to more accurately compare the difference between them. The dynamic time warping algorithm can find the best alignment between the corresponding data points from the two curves, thereby generating the minimum Euclidean distance alignment sequence between the two curves, so that the time scale can be nonlinearly warped by stretching, and the obtained Euclidean distance is used to measure the similarity of the two curves. Then, the average dynamic time warping distance (DTW) between the two curves is calculated, which measures their similarity or difference. A distance threshold is preset. If the calculated average dynamic time warping distance is greater than this threshold, it is determined that there is an abnormal energy consumption condition, indicating that the energy consumption of the corresponding multi-sensing head module deviates significantly from the normal working state. After identifying the energy consumption anomaly, the source data corresponding to the current deviation timing curve is marked as abnormal data, and a traceability analysis is performed. It helps to track down the specific cause of the anomaly and the possible faulty module. According to the traceability analysis results, an early warning message of energy consumption anomaly is generated, indicating that the relevant multi-sensing head module may have a fault and needs further inspection and maintenance. This enables timely response when energy consumption anomaly occurs, providing detailed fault information to maintenance personnel, and ensuring the stability and efficiency of the system.

[0099] Figure 2 A flow chart of an energy consumption monitoring method applied to a multi-sensing head module provided by an embodiment of the present invention;

[0100] like Figure 2 As shown, the present invention provides a flow chart of an energy consumption monitoring method applied to a multi-sensing head module, comprising:

[0101] S202, obtaining normal energy consumption data when the multi-sensing head module monitors the target storage device, preset unit time steps, and processing the obtained normal energy consumption data into sequence data separated by the preset unit time steps;

[0102] S204, taking the energy consumption data corresponding to each unit time step as a state vector, using the Markov algorithm to calculate the probability value of each state vector in the state vector matrix transferring to another state vector, and generating a state transfer matrix;

[0103] S206, combining the state transfer matrix and the corresponding normal energy consumption data to form a training data set to train the energy status perception model, and outputting the trained energy status perception model;

[0104] S208, obtaining real-time energy consumption monitoring information when the multi-sensing head module monitors the target storage device, inputting it into the energy status perception model to obtain a final reconstruction sequence, generating a predicted value of energy consumption of the multi-sensing head module under normal conditions, and calculating a reconstruction error;

[0105] S210, calculating the predicted value of energy consumption of the multi-sensing head module under normal conditions and the real-time energy consumption monitoring information, obtaining the deviation between the predicted value and the actual value, and generating a deviation time series curve according to the time series characteristics;

[0106] S212, performing fitting based on the calculated reconstruction error to generate a reconstruction error timing curve, performing time series dynamic warping with the deviation timing curve, and calculating an average dynamic time warping distance between the deviation timing curve and the reconstruction error timing curve;

[0107] S214, judging whether there is abnormal energy consumption based on the average dynamic time regularization distance, and issuing a maintenance warning.

[0108] It should be noted that in the scenario of anti-leakage monitoring of the target storage device, the multi-sensor head module installed at the monitoring position is used to detect the interval position, and the anti-leakage controller is used to perform data analysis and overall control to avoid leakage events. In the normal operating environment of the monitoring system, the corresponding energy consumption should always be at a normal level. If the energy consumption is abnormal, it may mean that there is a problem with the corresponding monitoring device. Whether the energy consumption increases or decreases, it will cause dangerous consequences. For example, the abnormal increase in energy consumption may cause a short circuit, which may cause the corresponding device to burn, further damage the storage device, and cause leakage or disasters. Therefore, it is necessary to monitor energy consumption to avoid problems. At the same time, whether it is the multi-sensor head module or the anti-leakage controller, the corresponding communication frequency should be within the normal range limit, which means that the corresponding energy consumption within the set period also has a corresponding normal range. When the energy consumption is abnormal, it may mean that the corresponding monitoring device has a communication abnormality. If the energy consumption increases, it may mean that some monitoring devices have communicated multiple times within a fixed period; if the energy consumption decreases, it may mean that some monitoring devices have communicated less times within a fixed period, and there is also an abnormal problem. By monitoring and analyzing energy consumption, we can further control the normal operation of various monitoring devices in the area to improve the operating efficiency and safety of the monitoring system.

[0109] Figure 3 A multi-sensor head wireless communication control system 3 based on a water leakage prevention controller is provided in one embodiment of the present invention. The system includes: a memory 31 and a processor 32. The memory 31 contains a multi-sensor head wireless communication control method program based on a water leakage prevention controller. When the multi-sensor head wireless communication control method program based on a water leakage prevention controller is executed by the processor 32, the following steps are implemented:

[0110] Obtain the storage device structure information of the target area, extract the storage device structure characteristics to analyze the leakage-prone areas of the storage device, and formulate the leakage sensor head module placement plan and anti-leakage controller plan for the target storage device;

[0111] Set the wireless communication rules between the sensor head module and the water leakage prevention controller, obtain the monitoring data of several associated multi-sensor head modules at a preset collection frequency based on the data collection rules, and perform data collision detection and control;

[0112] Monitor the storage status of the target storage device to obtain storage device monitoring information, analyze whether there is a leak and the extent of the leak, and provide early warning prompts and leak control;

[0113] An energy status perception model is built based on a generative adversarial network to monitor the real-time energy consumption of the multi-sensing head module, analyze whether there is any energy consumption abnormality, and provide maintenance prompts.

[0114] In the several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as: multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling, direct coupling, or communication connection between the components shown or discussed can be through some interfaces, and the indirect coupling or communication connection of the devices or units can be electrical, mechanical or other forms.

[0115] The units described above as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units; they may be located in one place or distributed on multiple network units; some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0116] In addition, all functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integrated units may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0117] Those skilled in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, read-only memories (ROM, Read-Only Memory), random access memories (RAM, Random Access Memory), disks or optical disks, and other media that can store program codes.

[0118] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, ROM, RAM, magnetic disks or optical disks.

[0119] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. Therefore, the protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A multi-sensor head wireless communication control method based on a water leakage prevention controller, characterized in that: include: Obtain the storage device structure information of the target area, extract the storage device structure characteristics to analyze the leakage-prone areas of the storage device, and formulate the leakage sensor head module placement plan and anti-leakage controller plan for the target storage device; Set the wireless communication rules between the sensor head module and the water leakage prevention controller, obtain the monitoring data of several associated multi-sensor head modules at a preset collection frequency based on the data collection rules, and perform data collision detection and control; Monitor the storage status of the target storage device to obtain storage device monitoring information, analyze whether there is a leak and the extent of the leak, and provide early warning prompts and leak control; An energy status perception model is built based on a generative adversarial network to monitor the real-time energy consumption of the multi-sensing head module, analyze whether there is any energy consumption abnormality, and provide maintenance prompts.

2. According to claim 1, a multi-sensor head wireless communication control method based on a water leakage prevention controller is characterized in that: The method of extracting the structural features of the storage device to analyze the leak-prone areas of the storage device and formulating a placement plan for the leakage sensing head module and a water leakage prevention controller for the target storage device specifically includes: Acquire storage device construction information of a target area, perform feature extraction on the storage device construction information, and obtain storage device construction feature information, wherein the storage device construction feature information includes storage device structure features and storage device material features; Through data retrieval, water leakage instances of target storage devices with several storage specifications are obtained, features are extracted from each historical instance, and the extracted features are classified into categories based on the storage specifications to construct an instance data set; Based on the cosine metric algorithm, the storage device structural feature information is matched and analyzed with the feature data in the instance data set, and the leak-prone area of ​​the target storage device is analyzed to obtain leak-prone area analysis information; According to the leak-prone area analysis information, the historical leakage frequency of the corresponding area is obtained through the instance data set as a priority indicator, and the priority of each leak-prone area is defined to obtain priority analysis information; A leakage sensing head module placement plan for the target storage device is formulated in combination with the leakage-prone area analysis information and the priority analysis information, the leakage sensing head module is placed in the target storage device, and a water leakage prevention controller is set based on the actual monitoring area and the priority of the placement area.

3. According to claim 1, a multi-sensor head wireless communication control method based on a water leakage prevention controller is characterized in that: The wireless communication rules between the sensor head module and the water leakage prevention controller are set, and the monitoring data of several associated multi-sensor head modules are acquired at a preset acquisition frequency based on the data acquisition rules, and data collision detection and control are performed, specifically including: Based on the TDMA mechanism, a fixed data transmission time slot is allocated to each sensor head module, and the LoRa protocol is used to set the wireless communication rules between the sensor head module and the anti-leakage controller; The data collection rules of the water leakage prevention controller are set. The water leakage prevention controller obtains the monitoring data of several associated multi-sensing head modules at a preset collection frequency based on the data collection rules, and performs data collision detection; By sending a test command to each multi-sensing head module to obtain a feedback signal, it is determined whether a collision occurs based on the obtained feedback signal. If the number of data packets received per unit time is greater than a preset threshold, it indicates that a collision occurs; Obtain the conflict data of the collision and perform feature extraction, extract the identification features of the conflict data, take the minimum average response time as the optimization goal, introduce the PSO algorithm to use the identification features of the conflict data to initialize the particle swarm, and iterate the analysis to obtain the first analysis information; A collision control strategy is generated based on the first analysis information to control the multiple sensor head modules within the jurisdiction.

4. According to the method of wireless communication control of multiple sensing heads based on water leakage prevention controller in claim 1, it is characterized in that: The monitoring of the storage status of the target storage device to obtain storage device monitoring information, analyzing whether leakage occurs and the extent of leakage, and providing early warning prompts and leakage control specifically includes: Based on data retrieval, historical monitoring data of the multi-sensor head module under different leakage degrees are obtained to form a first data set, leakage degree categories are defined and the corresponding historical monitoring data are associated, and monitoring data features of each leakage degree category are extracted according to the association results; A leakage perception model is constructed based on the noise reduction autoencoder structure, Gaussian noise is added to the extracted monitoring data features of each leakage degree category, and feature encoding is performed using a multi-layer perceptron. The encoded monitoring data feature data is input into the LSTM network for time series feature extraction, the extracted time series features are decoded and dimensionally upgraded, and then input into the leakage perception model for iterative training until a leakage perception model that meets the expectations is obtained; The storage status of the target storage device is monitored by arranging a plurality of multi-sensing head modules, storage device monitoring information is acquired, and data preprocessing is performed on the storage device monitoring information to obtain preprocessing information; Preset a timestamp, perform time series processing on the preprocessed information according to the timestamp to generate a time series sequence, input the sequence into the leakage perception model for analysis, and obtain leakage perception analysis information; Based on the leakage perception analysis information, it is determined whether the target storage device has a leakage risk, and a leakage warning report is generated to indicate the area and extent of the leakage. The corresponding leakage control strategy is obtained to generate a control instruction and send it to the water leakage prevention controller for control.

5. According to claim 1, a multi-sensor head wireless communication control method based on a water leakage prevention controller is characterized in that: The energy status perception model is constructed based on the generative adversarial network to monitor the real-time energy consumption of the multi-sensing head module, analyze whether there is energy consumption abnormality, and provide maintenance prompts, specifically including: Acquire normal energy consumption data when the multi-sensing head module monitors the target storage device, preset a unit time step, and process the acquired normal energy consumption data into sequence data separated by the preset unit time step; The energy consumption data corresponding to each unit time step is taken as a state vector, and each state vector is subjected to dimensionality reduction processing, and a state vector matrix after dimensionality reduction is constructed. The Markov algorithm is used to calculate the probability value of each state vector in the state vector matrix transferring to another state vector; An energy status perception model is built based on a generative adversarial network. The state transition matrix is ​​generated through the calculated state transition probability to characterize the transition relationship between each state vector. The training data set is combined with the corresponding normal energy consumption data to train the energy status perception model. Acquire real-time energy consumption monitoring information when the multi-sensing head module monitors the target storage device, perform time series processing on the real-time energy consumption monitoring information, and input the processed time series sequence into the energy status perception model; The input real-time energy consumption monitoring data sequence is taken as the original sequence, the state transfer matrix is ​​obtained and the generator is used to generate a reconstructed sequence, the reconstructed sequence is input into the discriminator to determine whether to accept the current reconstructed sequence, and iterative generation and judgment are performed to obtain the final reconstructed sequence.

6. A multi-sensor head wireless communication control method based on a water leakage prevention controller according to claim 1, characterized in that: The energy status perception model is constructed based on the generative adversarial network to monitor the real-time energy consumption of the multi-sensing head module, and analyze whether there is abnormal energy consumption, and provide maintenance prompts, and also includes: Generate a predicted value of energy consumption of the multi-sensing head module under normal conditions according to the final reconstruction sequence, and calculate a reconstruction error according to the final reconstruction sequence and the original sequence; Acquire real-time energy consumption monitoring information, calculate the predicted value of energy consumption of the multi-sensing head module under normal conditions and the real-time energy consumption monitoring information, and obtain the deviation between the predicted value and the actual value; Performing average filtering on the calculated deviation values, generating a deviation time series curve based on the filtered deviation values ​​according to the time series characteristics, and performing fitting based on the calculated reconstruction errors to generate a reconstruction error time series curve; Performing dynamic time warping on the deviation timing curve and the reconstruction error timing curve based on a dynamic warping algorithm, and calculating an average dynamic time warping distance between the deviation timing curve and the reconstruction error timing curve; A preset distance threshold is set. When the average dynamic time warping distance is greater than the preset distance threshold, it indicates that there is an abnormal energy consumption condition. Then the source data corresponding to the current deviation timing curve is marked as abnormal data for source tracing analysis. Based on the traceability analysis results, abnormal energy consumption warning information is generated, indicating that the corresponding multi-sensor head module has an abnormality and needs to be repaired.

7. A multi-sensor head wireless communication control system based on a water leakage prevention controller, characterized in that: The system includes: a memory and a processor, wherein the memory contains a multi-sensor head wireless communication control method program based on a water leakage prevention controller, and when the multi-sensor head wireless communication control method program based on a water leakage prevention controller is executed by the processor, the following steps are implemented: Obtain the storage device structure information of the target area, extract the storage device structure characteristics to analyze the leakage-prone areas of the storage device, and formulate the leakage sensor head module placement plan and anti-leakage controller plan for the target storage device; Set the wireless communication rules between the sensor head module and the water leakage prevention controller, obtain the monitoring data of several associated multi-sensor head modules at a preset collection frequency based on the data collection rules, and perform data collision detection and control; Monitor the storage status of the target storage device to obtain storage device monitoring information, analyze whether there is a leak and the extent of the leak, and provide early warning prompts and leak control; An energy status perception model is built based on a generative adversarial network to monitor the real-time energy consumption of the multi-sensing head module, analyze whether there is any energy consumption abnormality, and provide maintenance prompts.

Images