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

Abstract

The application discloses a kind of based on the multi-induction head wireless communication management and control method and system of water leakage prevention controller, comprising: obtaining storage device configuration information, extract storage device configuration feature analysis the easy leakage area of storage device, and formulate target storage device's leakage induction head module placement scheme and water leakage prevention controller scheme;Set the wireless communication rule between induction head module and water leakage prevention controller, based on data acquisition rule with preset acquisition frequency obtains the monitoring data of several associated multi-induction head modules, and carries out data collision detection and control;The storage state of target storage device is monitored to obtain storage device monitoring information, analyze whether leakage occurs and leakage degree, and carry out early warning and leakage control;Based on energy status perception model is constructed to the generative adversarial network, monitor the real-time energy consumption of multi-induction head module, and analyze whether there is energy consumption anomaly, carry out maintenance prompt. Improve the accuracy and intelligence of water leakage monitoring.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of water leakage prevention equipment management and control, and particularly relates to a multi-sensing head wireless communication management and control method and system based on a water leakage prevention controller. BACKGROUND

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

[0003] In addition, although wireless monitoring technology has solved the wiring problem to some extent, in the multi-sensing head scenario, due to the lack of effective communication management and control mechanism, there are often problems of data transmission conflict, serious signal interference, and high delay, which leads to the fact that water leakage events cannot be captured and processed in time. At the same time, the running state of the sensing head and the controller is not monitored in real time, and the monitoring capability of the system may be reduced due to equipment failure or insufficient battery power, thereby affecting the reliability and real-time performance of water leakage early warning. SUMMARY

[0004] The present application overcomes the defects of the prior art and provides a multi-sensing head wireless communication management and control method and system based on a water leakage prevention controller, which aims to improve the accuracy and intelligence of water leakage monitoring.

[0005] To achieve the above-mentioned purpose, the first aspect of the present application provides a multi-sensing head wireless communication management and control method based on a water leakage prevention controller, comprising:

[0006] Obtaining the storage device structure information of the target area, extracting the storage device structure feature to analyze the easy leakage area of the storage device, and formulating the leakage sensing head module placement scheme and the water leakage prevention controller scheme of the target storage device;

[0007] Setting the wireless communication rules between the sensing head module and the water leakage prevention controller, obtaining the monitoring data of the associated several multi-sensing head modules based on the data acquisition rules at a preset acquisition frequency, and performing data collision detection and management and control;

[0008] Monitoring the storage state of the target storage device to obtain the storage device monitoring information, analyzing whether there is leakage and the leakage degree, and performing early warning and leakage control;

[0009] Based on the energy condition perception model constructed by the generative adversarial network, the real-time energy consumption of the multi-sensing head module is monitored, and whether there is energy consumption anomaly is analyzed, and maintenance prompt is performed.

[0010] In the scheme, the extraction storage device structure feature analysis storage device easy leakage area, and make the target storage device leakage sensing head module placement scheme and the anti-leakage controller, specifically comprising:

[0011] Obtain the storage device structure information of the target area, extract the features of the storage device structure information, and obtain the storage device structure feature information, which includes storage device structure features and storage device material features;

[0012] Obtain a plurality of storage specifications of the target storage device leakage instance through data retrieval, extract the features of each historical instance, and classify the extracted features according to the storage specifications as categories to construct an instance dataset;

[0013] Based on the cosine metric algorithm, the storage device structure feature information is matched and analyzed with the feature data in the instance dataset, the easy leakage area of the target storage device is analyzed, and the easy leakage area analysis information is obtained;

[0014] According to the easy leakage area analysis information, the historical leakage frequency of the corresponding area is obtained through the instance dataset as a priority index, the priority of each easy leakage area is defined, and the priority analysis information is obtained;

[0015] The leakage sensing head module placement scheme of the target storage device is formulated in combination with the easy leakage area analysis information and the priority analysis information, the leakage sensing head module is placed in the target storage device, and the anti-leakage controller is set based on the actual monitoring area and the priority of the placement area.

[0016] In the scheme, the wireless communication rule between the sensing head module and the anti-leakage controller is set, the monitoring data of the associated plurality of sensing head modules is obtained based on the data acquisition rule at a preset acquisition frequency, and data collision detection and control are performed, specifically comprising:

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

[0018] Set the data acquisition rule of the anti-leakage controller, and the anti-leakage controller obtains the monitoring data of the associated plurality of sensing head modules based on the data acquisition rule at a preset acquisition frequency, and performs data collision detection;

[0019] Obtain the feedback signal by sending a test instruction to each sensing head module, judge whether a collision occurs based on the obtained feedback signal, if the number of received data packets in a unit of time is greater than a preset threshold, it means that a collision occurs;

[0020] Collision data of the collision is acquired and feature extraction is performed, identification features of the collision data are extracted, a minimum average response time is taken as an optimization target, a PSO algorithm is introduced to initialize a particle swarm using the identification features of the collision data, and first analysis information is obtained through iterative analysis;

[0021] A collision regulation strategy is generated based on the first analysis information, and the multiple sensing head modules in the jurisdiction area are regulated and controlled.

[0022] In this scheme, the storage state of the target storage device is monitored to obtain storage device monitoring information, whether leakage occurs and the degree of leakage are analyzed, and early warning and leakage control are performed, specifically including:

[0023] Based on data retrieval, historical monitoring data of the multiple sensing head modules 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 result;

[0024] A leakage perception model is constructed according to a denoising auto-encoding structure, Gaussian noise is added to the extracted monitoring data features of each leakage degree category, and a multi-layer perception machine is used for feature encoding;

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

[0026] The storage state of the target storage device is monitored by arranging a plurality of multiple sensing head modules, and storage device monitoring information is obtained, and the storage device monitoring information is data preprocessed to obtain preprocessed information;

[0027] A preset timestamp is set, the preprocessed information is time-sequenced according to the timestamp to generate a time sequence, and input into the leakage perception model for analysis to obtain leakage perception analysis information;

[0028] According to the leakage perception analysis information, it is determined whether the target storage device has a leakage risk, and a leakage warning report is generated, the area and degree of leakage are prompted, and the corresponding leakage control strategy is obtained to generate a control instruction and send it to a leak-proof water controller for control.

[0029] In this scheme, the energy status perception model is constructed based on a generative adversarial network, the real-time energy consumption of the multiple sensing head modules is monitored, and whether there is an energy consumption anomaly is analyzed, and a maintenance prompt is performed, specifically including:

[0030] The normal energy consumption data of the target storage device monitored by the multi-sensing head module is acquired, a preset unit time step is set, and the acquired normal energy consumption data is processed 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, each state vector is processed by dimension reduction, and a state vector matrix after dimension reduction is constructed, and a state transition probability value of each state vector in the state vector matrix to another state vector is calculated by using a Markov algorithm;

[0032] An energy condition perception model is constructed based on a generative adversarial network, a state transition matrix is generated by calculating the state transition probability, which is used to represent the transition relationship between the state vectors, and the corresponding normal energy consumption data is combined to form a training data set to train the energy condition perception model;

[0033] Real-time energy consumption monitoring information of the target storage device monitored by the multi-sensing head module is acquired, and the real-time energy consumption monitoring information is processed in time sequence, and the processed time sequence is input into the energy condition perception model;

[0034] The input real-time energy consumption monitoring data sequence is taken as an original sequence, a state transition matrix is acquired, and a generator is used to generate a reconstructed sequence, the reconstructed sequence is input into a discriminator to determine whether to accept the current reconstructed sequence, and the final reconstructed sequence is obtained by iterative generation and determination.

[0035] In the scheme, the energy condition perception model is constructed based on the generative adversarial network, the real-time energy consumption of the multi-sensing head module is monitored, and whether there is an energy consumption anomaly is analyzed, maintenance is prompted, and the scheme further comprises:

[0036] An energy consumption prediction value of the multi-sensing head module under normal conditions is generated according to the final reconstructed sequence, and a reconstruction error is calculated according to the final reconstructed sequence and the original sequence;

[0037] The real-time energy consumption monitoring information is acquired, the energy consumption prediction value of the multi-sensing head module under normal conditions is operated with the real-time energy consumption monitoring information, and a deviation between the prediction value and the actual value is acquired;

[0038] The calculated deviation value is subjected to mean value filtering, the filtered deviation value is generated into a deviation time sequence curve according to the time sequence characteristics, and a reconstruction error time sequence curve is generated by fitting based on the calculated reconstruction error;

[0039] The deviation time sequence curve and the reconstruction error time sequence curve are subjected to time sequence dynamic normalization based on a dynamic normalization algorithm, and an average dynamic time normalization distance between the deviation time sequence curve and the reconstruction error time sequence curve is calculated;

[0040] A preset distance threshold, when the average dynamic time warping distance is greater than the preset distance threshold, represents that there is an energy consumption abnormal condition, and then the source data corresponding to the current deviation time curve is marked as abnormal data for traceability analysis.

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

[0042] The second aspect of the application provides a multi-sensing head wireless communication management and control system based on a water leakage prevention controller, which comprises a memory and a processor, the memory contains a multi-sensing head wireless communication management and control method based on a water leakage prevention controller, and the multi-sensing head wireless communication management and control method based on a water leakage prevention controller is implemented when the processor executes the following steps:

[0043] Obtain the storage device construction information of the target area, extract the storage device construction features to analyze the easy-leakage area of the storage device, and develop a leakage sensing head module placement scheme and a water leakage prevention controller scheme for the target storage device;

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

[0045] Monitor the storage state of the target storage device to obtain the storage device monitoring information, analyze whether there is leakage and the leakage degree, and perform early warning and leakage control;

[0046] Based on the generated adversarial network, an energy status perception model is constructed to monitor the real-time energy consumption of the multi-sensing head module, analyze whether there is an energy consumption abnormality, and perform maintenance prompting.

[0047] The application discloses a multi-sensing head wireless communication management and control method and system based on a water leakage prevention controller, which comprises: obtaining storage device construction information, extracting storage device construction features to analyze the easy-leakage area of the storage device, and developing a leakage sensing head module placement scheme and a water leakage prevention controller scheme for the target storage device; setting the wireless communication rules between the sensing head module and the water leakage prevention controller, obtaining the monitoring data of the associated multi-sensing head modules at a preset acquisition frequency based on the data acquisition rules, and performing data collision detection and management and control; monitoring the storage state of the target storage device to obtain the storage device monitoring information, analyzing whether there is leakage and the leakage degree, and performing early warning and leakage control; based on the generated adversarial network, an energy status perception model is constructed to monitor the real-time energy consumption of the multi-sensing head module, analyze whether there is an energy consumption abnormality, and perform maintenance prompting. The accuracy and intelligence of water leakage monitoring are improved. BRIEF DESCRIPTION OF DRAWINGS

[0048] In order to more clearly illustrate the technical solutions in the embodiments or examples of the present application, the drawings needed to be used in the embodiments or examples will be briefly introduced. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative effort based on these drawings.

[0049] Figure 1 A flow chart of a multi-sensing head wireless communication management and control method based on a water leakage prevention controller is provided for an embodiment of the present application.

[0050] Figure 2 A flow chart of an energy consumption monitoring method applied to a multi-sensing head module is provided for an embodiment of the present application.

[0051] Figure 3 A block diagram of a multi-sensing head wireless communication management and control system based on a water leakage prevention controller is provided for an embodiment of the present application.

[0052] The implementation, functional features and advantages of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION

[0053] In order to more clearly illustrate the technical solutions in the embodiments or examples of the present application, the drawings needed to be used in the embodiments or examples will be briefly introduced. Obviously, the drawings in the following description only constitute some embodiments of the present application, and for those skilled in the art, other drawings can be obtained without creative effort based on these drawings.

[0054] In the following description, many specific details are set forth in order to provide a thorough understanding of the present application, however, the present application can also be implemented in other ways different from those described herein, therefore, the scope of protection of the present application is not limited by the specific embodiments disclosed below.

[0055] Figure 1 A flow chart of a multi-sensing head wireless communication management and control method based on a water leakage prevention controller is provided for an embodiment of the present application.

[0056] As shown in the flow chart of a multi-sensing head wireless communication management and control method based on a water leakage prevention controller, the present application comprises: Figure 1 S102, obtaining storage device construction information of a target area, extracting storage device construction features to analyze the leakage-prone areas of the storage device, and formulating a leakage sensing head module placement scheme and a water leakage prevention controller scheme for the target storage device.

[0057]

[0058] ​S104, set the wireless communication rule between the induction head module and the water leakage prevention controller, acquire the monitoring data of the associated several multi-induction head modules based on the data acquisition rule at a preset acquisition frequency, and perform data collision detection and control;

[0059] S106, monitor the storage state of the target storage device to acquire storage device monitoring information, analyze whether leakage occurs and the leakage degree, and perform early warning and leakage control;

[0060] S108, based on the generated adversarial network, construct an energy status perception model, monitor the real-time energy consumption of the multi-induction head module, analyze whether there is an abnormal energy consumption, and perform maintenance prompt.

[0061] It should be noted that the present application provides a multi-induction head wireless communication control method and system based on a water leakage prevention controller. By analyzing the physical characteristics of the device structure and the statistical rules of historical leakage data, the accurate positioning of high-risk areas is ensured, and the easy-to-leak areas of the device are identified. An optimized placement scheme for the leakage induction head module of the target storage device is developed to maximize the monitoring coverage. At the same time, a water leakage prevention controller scheme is designed to ensure that the system can quickly respond and take appropriate control measures when leakage is detected. Then, a clear communication protocol and rule are set to ensure the efficiency and reliability of data transmission. Based on the pre-prepared data acquisition rule, monitoring data is collected from multiple induction head modules at a preset frequency and data collision detection and control are performed to avoid signal conflicts caused by multiple induction heads sending data at the same time, thereby ensuring the integrity and real-time of the data. Further, the storage state of the target storage device is comprehensively analyzed to determine whether there is a leakage. If leakage is detected, the corresponding early warning and leakage control measures are triggered according to the real-time situation, such as closing the water source in a specific area or starting the leakage handling device. In addition, by monitoring the real-time energy consumption of the induction head module, it is dynamically analyzed whether there is an abnormal energy consumption. For example, if the energy consumption of some induction head modules is much higher than that of other modules, it may indicate that the device has failed or the environmental conditions have affected its normal operation. Through energy anomaly analysis results, maintenance personnel are provided with maintenance prompts to ensure the long-term stable operation of the entire monitoring system. The water leakage prevention capability and system reliability of the storage device are effectively improved.

[0062] Further, in a preferred embodiment of the present application, the extraction storage device structure feature analyzes the easy-to-leak area of the storage device, and develops a leakage induction head module placement scheme for the target storage device and a water leakage prevention controller, specifically including:

[0063] Obtaining storage device structure information of a target area, performing feature extraction on the storage device structure information to obtain storage device structure feature information, the storage device structure feature information including storage device structure features and storage device material features;

[0064] Obtaining water leakage instances of target storage devices of several storage specifications through data retrieval, performing feature extraction on each historical instance, and classifying the extracted features according to storage specifications as categories to construct an instance data set;

[0065] Performing matching analysis on the storage device structure feature information and feature data in the instance data set based on a cosine metric algorithm to analyze the easy-leakage areas of the target storage device and obtain easy-leakage area analysis information;

[0066] Obtaining the historical leakage frequency of the corresponding area through the instance data set according to the easy-leakage area analysis information as a priority index, defining the priority of each easy-leakage area, and obtaining priority analysis information;

[0067] Formulating a leakage sensing head module placement scheme for the target storage device in combination with the easy-leakage area analysis information and the priority analysis information, placing a leakage sensing head module in the target storage device, and setting a water leakage prevention controller 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 acquired 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 shape, connection points and possible weak links of the device, while the material features include the material types, corrosion resistance and pressure resistance of the device, etc. These features collectively reflect the potential water leakage risk points of the device. Next, a plurality of historical water leakage instances of target storage devices with similar storage specifications are collected through data retrieval means. After detailed feature extraction of these water leakage instances, the extracted features are classified according to the storage specifications to form an instance data set. Based on the cosine metric algorithm, the construction feature information of the storage device is matched and analyzed with the feature data in the instance data set. This algorithm identifies the similar parts of the target storage device in terms of construction and material features with the water leakage devices in the historical instances by calculating the similarity between the features, and points out the specific areas in the device where leakage is most likely to occur. Further, the historical leakage frequency of these areas is extracted from the instance data set as a priority indicator. By analyzing and comparing the leakage frequency of each vulnerable area, the system defines the priority of these areas. For example, areas with higher leakage frequency are assigned higher priority. Finally, combining the vulnerable area analysis information and the priority analysis information, a leakage sensing head module placement scheme for the target storage device is developed. In this scheme, the sensing head module is placed in high-priority areas first, and covers other vulnerable areas to achieve comprehensive monitoring. At the same time, according to the actual monitoring area and the priority of the area, a water leakage prevention controller is set to achieve efficient management and analysis of the sensing head module data, ensuring a quick response when leakage is detected.

[0069] Further, in a preferred embodiment of the present application, the wireless communication rules between the sensing head module and the water leakage prevention controller are set based on the data acquisition rules to acquire the monitoring data of the associated plurality of sensing head modules at a preset acquisition frequency, and perform data collision detection and control. Specifically, it includes:

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

[0071] The data acquisition rules of the water leakage prevention controller are set, and the water leakage prevention controller acquires the monitoring data of the associated plurality of sensing head modules at a preset acquisition frequency based on the data acquisition rules, and performs data collision detection;

[0072] By sending test instructions to each sensing head module to obtain feedback signals, it is judged whether a collision occurs based on the obtained feedback signals. If the number of received data packets per unit time is greater than a preset threshold, it means that a collision has occurred;

[0073] The collision data is obtained and feature extraction is performed, the identification features of the collision data are extracted, the minimum average response time is taken as an optimization target, the PSO algorithm is introduced to initialize the particle swarm using the identification features of the collision data, and first analysis information is obtained through iterative analysis;

[0074] A collision regulation strategy is generated based on the first analysis information, and the multiple sensing head modules in the jurisdiction area are regulated and controlled.

[0075] It should be noted that, in order to realize efficient wireless communication between the 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 modules and the anti-leakage controller, ensuring that data can be stably transmitted in a low-power, long-distance wireless transmission environment. Avoiding communication resource conflicts and improving transmission efficiency and reliability. In terms of data acquisition, the anti-leakage controller acquires 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 multiple sensing head modules are transmitting 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 within a unit of time exceeds the preset threshold, it is determined that a collision has occurred, indicating that multiple modules are attempting to transmit data simultaneously, resulting in communication conflicts. Further, the collision data is extracted and analyzed for its features. The identification features of the collision data include the source information of the data packet, the timestamp, and the collision frequency, etc. key attributes. In order to optimize the data transmission process, the particle swarm optimization (PSO) algorithm is introduced to minimize the average response time. First, the particle swarm is initialized using the identification features of the collision data, and through multiple iterative analyses, first analysis information is obtained to identify the optimal time slot allocation strategy to reduce the likelihood of data collision. Based on the first analysis information, a collision regulation strategy is generated to dynamically adjust the working mode and communication time slot allocation of the multiple sensing head modules. The sensing head modules in the jurisdiction area are effectively regulated and controlled to ensure that the transmission time of each module is orderly during the data acquisition process. The efficiency of wireless communication is improved, and the coordination ability of the sensing head modules is optimized, providing technical support for the anti-leakage controller to achieve accurate monitoring.

[0076] Further, in a preferred embodiment of the present application, the storage state of the target storage device is monitored to obtain storage device monitoring information, the occurrence of leakage and the degree of leakage are analyzed, and warning prompts and leakage control are performed, specifically including:

[0077] Based on data retrieval, historical monitoring data of multi-sensing head modules under different leakage levels are obtained to form a first data set, leakage level categories are defined, and corresponding historical monitoring data are associated, and monitoring data features of each leakage level category are extracted according to the association result;

[0078] According to the noise reduction auto-encoding structure, a leakage sensing model is constructed, Gaussian noise is added to the extracted monitoring data features of each leakage level category, and a multi-layer perception machine is used for feature coding;

[0079] The coded monitoring data feature data is input into the LSTM network for time sequence feature extraction, the extracted time sequence features are decoded and dimensioned, and input into the leakage sensing model for iterative training until the desired leakage sensing model is obtained;

[0080] The storage state of the target storage device is monitored by arranging a plurality of multi-sensing head modules, and storage device monitoring information is obtained, and the storage device monitoring information is preprocessed to obtain preprocessed information;

[0081] A preset timestamp is used to time sequence the preprocessed information to generate a time sequence, which is input into the leakage sensing model for analysis to obtain leakage sensing analysis information;

[0082] According to the leakage sensing analysis information, it is judged whether the target storage device has a leakage risk, and a leakage warning report is generated to prompt the area and degree of leakage, and the corresponding leakage control strategy is obtained to generate a control instruction sent to a leak-proof control device for control.

[0083] It should be noted that in order to comprehensively monitor and analyze the leakage risk of the target storage device, first, the historical monitoring data of the multi-sensing head module under different leakage degrees is obtained through data retrieval, a plurality of 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. A denoising auto-encoding structure is used to construct a leakage perception model. Gaussian noise is added to the extracted monitoring data features of each leakage degree category, and a multi-layer perception machine is used to encode these features to enhance the robustness of the model to data noise. Then, the encoded monitoring data features are input into a long short-term memory network (LSTM) to extract the time sequence features in the monitoring data. The LSTM network extracts deep features reflecting the dynamic changes of the leakage by analyzing the time sequence change pattern of the data. After decoding and dimensionality increasing of these time sequence features, they are input into the leakage perception model for iterative training. Through multiple iterations and optimization, the model gradually converges to the expected performance level. Then, the storage state of the target storage device is monitored in real time by arranging 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. And based on the preset timestamp, the preprocessed information is time-sequenced to generate data sequences with time sequence features. Input them into the leakage perception model for analysis to generate leakage perception analysis information. According to the leakage perception analysis information, the system determines whether the target storage device has a leakage risk. If a leakage risk is found, further analyze the specific area and severity of the leakage, obtain the corresponding leakage control strategy, generate control instructions, and send the instructions to the anti-leakage controller. The controller then takes necessary protective measures, such as shutting down related water sources or starting remediation equipment.

[0084] Further, in a preferred embodiment of the present application, the energy status perception model is constructed based on a generative adversarial network, the real-time energy consumption of the multi-sensing head module is monitored, and whether there is an energy consumption anomaly is analyzed to provide maintenance prompts. Specifically, it includes:

[0085] Obtain normal energy consumption data of the multi-sensing head module monitoring the target storage device, and predefine a unit time step. Process the obtained normal energy consumption data into sequence data separated by the pre-defined unit time step;

[0086] Take the energy consumption data corresponding to each unit time step as a state vector, perform dimensionality reduction processing on each state vector, and construct a state vector matrix after dimensionality reduction. Use Markov algorithm to calculate the probability value of each state vector in the state vector matrix transferring to another state vector;

[0087] The energy condition perception model is constructed based on a generative adversarial network, a state transition matrix is generated by calculating the state transition probability, and is used to represent the transition relationship between state vectors, and the corresponding normal energy consumption data is combined to form a training data set to train the energy condition perception model;

[0088] Real-time energy consumption monitoring information of the target storage device monitored by the multi-sensing head module is acquired, and the real-time energy consumption monitoring information is processed in time sequence, and the time sequence obtained by processing is input into the energy condition perception model;

[0089] The input real-time energy consumption monitoring data sequence is taken as an original sequence, a state transition matrix is acquired and a generator is used to generate a reconstructed sequence, the reconstructed sequence is input into a discriminator to determine whether to accept the current reconstructed sequence, and the final reconstructed sequence is obtained by iterative generation and determination.

[0090] It should be noted that, first, the energy consumption data of the multi-sensing head module in the normal working state is acquired. The acquired normal energy consumption data is divided into sequence data separated by a preset unit time step. Each state vector is processed in dimension reduction, and a state vector matrix is formed according to the state vectors after dimension reduction. The probability value of each state vector in the state vector matrix to other state vectors is calculated by using the Markov algorithm. A state transition matrix is generated by these probability values, which represents the dynamic transition relationship between different state vectors. Then, an energy condition perception model is constructed based on a generative adversarial network (GAN). The generative adversarial network is composed of a generator and a discriminator. The state transition matrix calculated and the corresponding normal energy consumption data are used to generate a training data set, and the energy condition perception model is trained by using the data set. Through this process, the model can learn the time sequence characteristics and change rules of the normal energy consumption state. Then, the energy consumption monitoring information of the multi-sensing head module is acquired in real time, and is processed in time sequence and input into the energy condition perception model. The model takes the real-time data sequence as the original sequence, and analyzes it in combination with the state transition matrix learned in the training. The generator generates a reconstructed sequence according to the input state information, which is an approximate prediction of the original sequence. Then, the reconstructed sequence is input into the discriminator, which judges 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] Further, in a preferred embodiment of the present application, the energy condition perception model is constructed based on a generative adversarial network, the real-time energy consumption of the multi-sensing head module is monitored, and it is analyzed whether there is an energy consumption anomaly, a maintenance prompt is performed, and the method further comprises:

[0092] According to the final reconstruction sequence, an energy consumption prediction value of the multi-sensing head module under normal conditions is generated, and a reconstruction error is calculated according to the final reconstruction sequence and the original sequence;

[0093] Real-time energy consumption monitoring information is acquired, the energy consumption prediction value of the multi-sensing head module under normal conditions is operated with the real-time energy consumption monitoring information, and a deviation between the prediction value and an actual value is acquired;

[0094] The calculated deviation value is subjected to average value filtering, the filtered deviation value is used to generate a deviation time sequence curve according to a time sequence feature, and a reconstruction error time sequence curve is generated by fitting based on the calculated reconstruction error;

[0095] The deviation time sequence curve and the reconstruction error time sequence curve are subjected to time sequence dynamic normalization based on a dynamic normalization algorithm, and an average dynamic time normalization distance between the deviation time sequence curve and the reconstruction error time sequence curve is calculated;

[0096] A preset distance threshold value is set, when the average dynamic time normalization distance is greater than the preset distance threshold value, it represents that there is an energy consumption abnormal condition, and then the source data corresponding to the current deviation time sequence curve is marked as abnormal data for traceability analysis;

[0097] Based on the traceability analysis result, energy consumption abnormal early warning information is generated, and it is prompted that the corresponding multi-sensing head module has an abnormality and needs to be repaired.

[0098] It should be noted that after obtaining the final reconstructed sequence, it represents the predicted value of energy consumption of the multi-sensing head module under normal working condition. By comparing the final reconstructed sequence with the original monitoring data, the reconstruction error is calculated, which reflects the deviation between the predicted value and the actual monitoring value. Next, real-time energy consumption monitoring information is obtained, and the predicted value of energy consumption under normal condition is calculated with the real-time data, and the deviation between the predicted value and the actual value is calculated. The average value of the calculated deviation value is filtered to eliminate noise and smooth the data. The filtered deviation value generates a deviation time sequence curve according to the time sequence characteristics. At the same time, based on the calculated reconstruction error, a reconstruction error time sequence curve is generated to represent the error change between the predicted and actual data. Next, based on the dynamic scaling algorithm, the deviation time sequence curve and the reconstruction error time sequence curve are dynamically scaled in time sequence, and the time axis of the two curves is adjusted to more accurately compare the difference between them. The dynamic time scaling algorithm can find the best alignment between the corresponding data points in 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. The 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, and if the calculated average dynamic time warping distance is greater than the threshold, it is determined that there is an energy consumption anomaly, 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 deviation time sequence curve is marked as abnormal data, and traceability analysis is performed. Help to track the specific reason and possible fault module of the anomaly. According to the traceability analysis result, the energy consumption anomaly warning information is generated, prompting that the related multi-sensing head module may malfunction and needs to be further checked and repaired. Thus, timely response can be made when energy consumption anomaly occurs, and detailed fault information is provided for maintenance personnel to ensure 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 is provided for an embodiment of the present application;

[0100] As Figure 2 shown, the present application 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 of the multi-sensing head module monitoring target storage device at a preset unit time step, and processing the obtained normal energy consumption data into sequence data separated by the preset unit time step;

[0102] S204, taking the energy consumption data corresponding to each unit time step as a state vector, using 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 transition matrix;

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

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

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

[0106] S212, fitting the reconstruction error time sequence curve based on the calculated reconstruction error, time sequence dynamic normalization of the deviation time sequence curve, and calculation of the average dynamic time normalization distance between the deviation time sequence curve and the reconstruction error time sequence curve;

[0107] S214, judging whether there is an abnormal energy consumption condition according to the average dynamic time normalization distance, and performing maintenance warning.

[0108] It should be noted that in the scene of monitoring the target storage device for water leakage, the interval position is detected by the multi-sensing head module installed at the monitoring position, and the data is analyzed and overall controlled by the water leakage controller to avoid the existence of leakage events. In the normal operation environment of the monitoring system, the corresponding energy consumption should always be at a normal level. If the energy consumption is abnormal, it may represent a problem with the corresponding monitoring device. Whether the energy consumption increases or decreases will cause dangerous consequences. For example, an abnormal increase in energy consumption may cause a short circuit, which may cause the corresponding device to burn out and further damage the storage device, resulting in leakage or disaster. Therefore, the energy consumption needs to be monitored to avoid problems. At the same time, whether it is a multi-sensing head module or a water leakage controller, the corresponding communication frequency should be within the normal range of limits, which means that the corresponding energy consumption also has a corresponding normal range within the set period. When the energy consumption is abnormal, it may represent a communication abnormality of the corresponding monitoring device. If the energy consumption increases, it may represent that some monitoring devices have communicated multiple times within a fixed period. If the energy consumption decreases, it may represent that the communication frequency of some monitoring devices within a fixed period is reduced, which also has an abnormal problem. By monitoring and analyzing the energy consumption, the normal operation of various monitoring devices in the region is further controlled to improve the operation efficiency and safety of the monitoring system.

[0109] Figure 3 A multi-sensing head wireless communication control system based on a water leakage controller is provided for an embodiment of the application, which comprises a storage 31 and a processor 32. The storage 31 contains a multi-sensing head wireless communication control method program based on a water leakage controller. When the multi-sensing head wireless communication control method program based on the water leakage controller is executed by the processor 32, the following steps are implemented:

[0110] Obtain the storage device configuration information of the target area, extract the storage device configuration characteristics to analyze the leakage-prone area of the storage device, and develop a leakage sensing head module placement scheme and a water leakage controller scheme for the target storage device;

[0111] Set the wireless communication rules between the sensing head module and the water leakage controller, acquire the monitoring data of the associated multi-sensing head module at a preset acquisition frequency based on the data acquisition rules, and perform data collision detection and control;

[0112] Monitor the storage state of the target storage device to obtain storage device monitoring information, analyze whether there is leakage and the degree of leakage, and perform early warning and leakage control;

[0113] An energy condition perception model is constructed based on a generative adversarial network, the real-time energy consumption of the multi-sensing head module is monitored, and whether there is an energy consumption abnormality is analyzed to provide a maintenance prompt.

[0114] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other manners. The described device embodiments are merely illustrative, for example, the division of the units is only a logical function division, and there can be another division manner in actual implementation, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling, or direct coupling or communication connection between the components can be indirect coupling or communication connection through some interfaces, devices or units, and can be electrical, mechanical or in other forms.

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

[0116] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; and the integrated unit can be implemented in the form of hardware, or in the form of hardware plus software functional units.

[0117] Those of ordinary skill in the art can understand that all or part of the steps of the above method embodiments can be completed by a program instructing related hardware, and the foregoing program can be stored in a computer readable storage medium, and when the program is executed, the steps of the method embodiments are executed; and the foregoing storage medium includes: a mobile storage device, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0118] Alternatively, the above-mentioned integrated unit of the present application, if realized in the form of a software function module and sold or used as an independent product, can also be stored in a computer-readable storage medium. Based on such an understanding, the technical solutions of the embodiments of the present application can be embodied in the form of a software product, and the computer software product is stored in a storage medium, including a number of instructions to make a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the methods described in the embodiments of the present application. The aforementioned storage medium includes: mobile storage devices, ROM, RAM, magnetic disks or optical disks, and various media that can store program codes.

[0119] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A multi-sensor head wireless communication management method based on a water leakage prevention controller, characterized in that, The application relates to a storage device leakage monitoring method and device. The application comprises the following steps: acquiring storage device structure information of a target region, extracting storage device structure features, analyzing easy-to-leak regions of the storage device, and formulating a leakage sensing head module placement scheme and a leakage-proof controller scheme for the target storage device; setting a wireless communication rule between the sensing head module and the leakage-proof controller, acquiring monitoring data of a plurality of sensing head modules associated with the leakage-proof controller based on a data acquisition rule at a preset acquisition frequency, and performing data collision detection and control; monitoring the storage state of the target storage device to acquire storage device monitoring information, analyzing whether leakage occurs and the leakage degree, and performing early warning and leakage control; constructing an energy status sensing model based on a generative adversarial network, monitoring real-time energy consumption of the plurality of sensing head modules, analyzing whether energy consumption is abnormal, and performing maintenance prompting; The setting of the wireless communication rule between the sensing head module and the leakage-proof controller, the acquisition of the monitoring data of the plurality of sensing head modules associated with the leakage-proof controller based on the data acquisition rule at the preset acquisition frequency, and the data collision detection and control specifically comprise the following steps: allocating a fixed data transmission time slot for each sensing head module based on a TDMA mechanism, and setting the wireless communication rule between the sensing head module and the leakage-proof controller by using a LoRa protocol; setting a data acquisition rule of the leakage-proof controller, and acquiring the monitoring data of the plurality of sensing head modules associated with the leakage-proof controller based on the data acquisition rule at the preset acquisition frequency, and performing data collision detection; acquiring feedback signals by sending test instructions to the plurality of sensing head modules, judging whether a collision occurs based on the acquired feedback signals, and if the number of received data packets in a unit time is greater than a preset threshold, it is determined that a collision occurs; acquiring collision data of the collision and extracting features of the collision data, taking the minimum average response time as an optimization target, introducing a PSO algorithm to initialize a particle swarm by using the identification features of the collision data, and iteratively analyzing to obtain first analysis information; generating a collision regulation strategy based on the first analysis information, and controlling the plurality of sensing head modules in a jurisdictional region; The monitoring of the storage state of the target storage device to acquire the storage device monitoring information, the analysis of whether leakage occurs and the leakage degree, and the early warning and leakage control specifically comprise the following steps: acquiring historical monitoring data of the plurality of sensing head modules under different leakage degrees based on data retrieval to form a first data set, defining a leakage degree category and associating the corresponding historical monitoring data, and extracting monitoring data features of each leakage degree category according to the association result; constructing a leakage sensing model according to a denoising self-encoding structure, adding Gaussian noise to the extracted monitoring data features of each leakage degree category, and using a multilayer perception machine to perform feature encoding; inputting the encoded monitoring data features into an LSTM network to extract time sequence features, decoding and dimensionally upgrading the extracted time sequence features, and inputting the time sequence features into the leakage sensing model for iterative training until a leakage sensing model meeting an expectation is obtained. The storage state of the target storage device is monitored by arranging a plurality of multi-sensing head modules, storage device monitoring information is obtained, the storage device monitoring information is pre-processed to obtain pre-processed information; A preset timestamp is set, the pre-processed information is time-sequenced according to the timestamp to generate a time sequence, and the time sequence is input into the leakage awareness model for analysis to obtain leakage awareness analysis information; According to the leakage awareness analysis information, it is judged whether the target storage device has a leakage risk, and a leakage warning report is generated to prompt the area and degree of leakage, and a corresponding leakage control strategy is obtained to generate a control instruction sent to a leak-proof water controller for control.

2. The multi-sensor head wireless communication management method based on the water leakage prevention controller according to claim 1, characterized in that, The extraction storage device structure feature analyzes the leakage-prone area of the storage device, and formulates the leakage sensing head module placement scheme of the target storage device and the leak-proof water controller scheme, specifically including: Obtain the storage device structure information of the target area, extract the features of the storage device structure information, and obtain the storage device structure feature information, including the storage device structure feature and the storage device material feature; Obtain a plurality of storage specification target storage device water leakage instances through data retrieval, extract features of each historical instance, and classify the extracted features according to the storage specification as a category to construct an instance data set; Based on the cosine metric algorithm, the storage device structure feature information is matched and analyzed with the feature data in the instance data set to analyze the leakage-prone area of the target storage device and obtain leakage-prone area analysis information; According to the leakage-prone area analysis information, the historical leakage frequency of the corresponding area is obtained from the instance data set as a priority indicator, and the priority of each leakage-prone area is defined to obtain priority analysis information; Combine the leakage-prone area analysis information and the priority analysis information to formulate the leakage sensing head module placement scheme of the target storage device, place the leakage sensing head module in the target storage device, and set the leak-proof water controller based on the actual monitoring area and the priority of the placement area.

3. The multi-sensor head wireless communication management method based on the water leakage prevention controller according to claim 1, characterized in that, The energy status awareness model is constructed based on the generative adversarial network, the real-time energy consumption of the multi-sensing head module is monitored, and whether there is an energy consumption anomaly is analyzed to provide maintenance prompts, specifically including: Obtain normal energy consumption data of the multi-sensing head module monitoring the target storage device, and preset a unit time step. The obtained normal energy consumption data is processed into sequence data separated by the preset unit time step; The energy consumption data corresponding to each unit time step is used as a state vector, each state vector is processed by dimension reduction, and a dimension-reduced state vector matrix 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; The energy status awareness model is constructed based on the generative adversarial network, a state transition matrix is generated by calculating the state transition probability, which is used to represent the transition relationship between state vectors, and the corresponding normal energy consumption data is used to form a training data set to train the energy status awareness model; The real-time energy consumption monitoring information of the target storage device is acquired when the multi-sensing head module is monitoring, the real-time energy consumption monitoring information is time-sequenced, and the time-sequenced sequence obtained by processing is input into an energy condition perception model. The input real-time energy consumption monitoring data sequence is taken as an original sequence, a state transition matrix is acquired, and a generator is used to generate a reconstructed sequence, the reconstructed sequence is input into a discriminator to determine whether to accept the current reconstructed sequence, and iteration is performed to generate and determine the final reconstructed sequence.

4. The multi-sensor head wireless communication management method based on the water leakage prevention controller according to claim 1, characterized in that, The energy condition perception model is constructed based on the generative adversarial network, the real-time energy consumption of the multi-sensing head module is monitored, and it is analyzed whether there is an energy consumption anomaly, a maintenance prompt is performed, and the method further comprises: The energy consumption prediction value of the multi-sensing head module under normal conditions is generated according to the final reconstructed sequence, and the reconstruction error is calculated according to the final reconstructed sequence and the original sequence. The real-time energy consumption monitoring information is acquired, the energy consumption prediction value of the multi-sensing head module under normal conditions is operated with the real-time energy consumption monitoring information, and the deviation between the prediction value and the actual value is acquired. The average value filtering is performed on the calculated deviation value, the filtered deviation value is used to generate a deviation time sequence curve according to the time sequence characteristics, and the reconstruction error time sequence curve is generated by fitting based on the calculated reconstruction error. The deviation time sequence curve and the reconstruction error time sequence curve are time-sequentially dynamically regularized based on a dynamic regularization algorithm, and the average dynamic time warping distance between the deviation time sequence curve and the reconstruction error time sequence curve is calculated. A distance threshold is preset, when the average dynamic time warping distance is greater than the preset distance threshold, it represents that there is an energy consumption anomaly, and the source data corresponding to the current deviation time sequence curve is marked as abnormal data for traceability analysis. Energy consumption anomaly warning information is generated based on the traceability analysis result, and it is prompted that the corresponding multi-sensing head module has an anomaly and needs to be maintained.

5. A multi-sensor head wireless communication management system based on a water leakage prevention controller, characterized in that, The system comprises a memory and a processor, the memory comprises a multi-sensing head wireless communication control method based on a water leakage prevention controller, and the multi-sensing head wireless communication control method based on the water leakage prevention controller is executed by the processor to realize the multi-sensing head wireless communication control method based on the water leakage prevention controller in any one of claims 1-4.

Images