摘要：【中文】本发明涉及一种防止预配料料仓粘仓的系统及工艺方法，包括低压水管路、高压水管路、仓内照明、固定料仓和活动料仓，仓内照明设置于固定料仓的顶部，低压水管路和高压水管路沿通廊墙壁下部铺设，低压水管路和高压水管路上均设有控制阀门，低压水管路与固定料仓内上部的仓内低压水管道连接，仓内低压水管道上每间隔一定距离设置一个低压水喷头，喷水方向对准固定料仓的内壁，高压水管路通过金属软管连接高压喷枪。通过高低压水配合使用，有效避免烧结供料料仓内部物料层层粘结，消除粘仓问题对生产稳定运行的冲击。且简单易行，投资少，不用专门进行停机改造，利用物料封堆停机后的短暂时间即可完成。 【EN】The invention relates to a system and a process method for preventing a pre-batching bin from being stuck to a bin, and the system comprises a low-pressure water pipeline, a high-pressure water pipeline, an in-bin lighting device, a fixed bin and a movable bin, wherein the in-bin lighting device is arranged at the top of the fixed bin, the low-pressure water pipeline and the high-pressure water pipeline are laid along the lower part of the wall of a corridor, control valves are respectively arranged on the low-pressure water pipeline and the high-pressure water pipeline, the low-pressure water pipeline is connected with the in-bin low-pressure water pipeline at the upper part in the fixed bin, a low-pressure water spray head is arranged on the low-pressure water pipeline in the bin at certain intervals. Through the cooperation of high-low pressure water, effectively avoid sintering feed bin inside material to bond layer upon layer, eliminate the impact of gluing the storehouse problem to production steady operation. The method is simple and easy to implement, has low investment, does not need special shutdown reconstruction, and can be completed within a short time after the material pile sealing shutdown.

摘要：【中文】本发明公开了一种移动空调出风异常提示方法，所述方法包括：移动空调开机运行；根据移动空调前侧出风口风速或后侧出风口风速确定是否发出出风口异常警报。本发明的有益效果是：使得当空调出现制冷效果差或频繁保护时，可以及时提醒用户检查。 【EN】The invention discloses a method for prompting abnormal air outlet of a mobile air conditioner, which comprises the following steps: starting up the mobile air conditioner for operation; and determining whether to send out an air outlet abnormal alarm or not according to the air speed of the front side air outlet or the rear side air outlet of the mobile air conditioner. The invention has the beneficial effects that: when the air conditioner is poor in refrigeration effect or frequently protected, a user can be reminded of checking in time.

摘要：【中文】本公开提出了一种用于音频场景分类的数据扩充方法及装置，该数据扩充方法首先基于LDA挖掘音频文档中的关键音频事件；其次，对每类音频场景，分别统计类内关键音频事件出现次数的概率分布、在每一出现次数下关键音频事件出现位置的概率分布以及在每一出现次数下，关键音频事件持续时长的概率分布；最后，根据统计得到的概率分布生成新音频文档。本公开提出的数据扩充方法由关键音频事件和非关键音频事件根据训练集中关键音频事件的概率分布生成新数据，这种方法生成的新数据能很好地模拟真实环境下的音频场景，因而能有效地提高模型的分类性能，在不同的网络结构下和不同的数据集上都具有良好的稳定性。 【EN】The data expansion method is based on the steps that firstly, key audio events in an audio document are mined on the basis of LDA; secondly, for each type of audio scene, respectively counting the probability distribution of the occurrence times of the key audio events in the type, the probability distribution of the occurrence positions of the key audio events under each occurrence time and the probability distribution of the duration of the key audio events under each occurrence time; and finally, generating a new audio document according to the probability distribution obtained by statistics. The data expansion method provided by the disclosure generates new data by key audio events and non-key audio events according to the probability distribution of the key audio events in a training set, and the new data generated by the method can well simulate the audio scene in a real environment, so that the classification performance of the model can be effectively improved, and the model has good stability under different network structures and different data sets.

摘要：【中文】本公开提出了一种音频场景分类方法及系统，对音频文档内每个音频片段基于稀疏编码求取分类信息，并用校准CNN模型对分类信息进行校准，获得校准分类信息；通过分类CNN模型获得预分类信息；然后将两种分类信息通过融合得到融合分类信息；对音频文档内所有音频片段的融合分类信息统计分析，获得分类结果。本公开采用神经网络对稀疏编码的分类信息进行校准，校准后的分类信息更加准确，有利于改善CNN网络的分类结果；本公开通过稀疏编码辅助改善CNN网络的分类结果，在训练数据量相对较少的情况下仍然能得到良好的分类性能，减少CNN网络对训练数据量的依赖性。 【EN】The present disclosure provides an audio scene classification method and system, which obtains classification information for each audio clip in an audio document based on sparse coding, and calibrates the classification information by using a calibration CNN model to obtain calibration classification information; obtaining pre-classification information through a classification CNN model; then fusing the two kinds of classified information to obtain fused classified information; and carrying out statistical analysis on the fusion classification information of all the audio segments in the audio document to obtain a classification result. According to the method, the neural network is adopted to calibrate the sparse coded classification information, the calibrated classification information is more accurate, and the improvement of the classification result of the CNN network is facilitated; according to the method, the classification result of the CNN is improved through sparse coding assistance, good classification performance can be obtained under the condition that the training data volume is relatively small, and the dependence of the CNN on the training data volume is reduced.

摘要：【中文】本发明公开了一种公交调度事件自动处置方法及装置，该方法包括获取当前资源和服务要求，根据服务要求，生成全天的未挂班次号的预发车时刻表，根据当前资源，为预发车时刻表中的发车时刻设置班次信息。通过当前资源和服务要求，自动生成发车计划以及自动完成发车，可以解决在调度的过程因为车辆、驾驶员以及外界环境的原因导致不能按照原来编制的计划进行发车的情况，不仅减少调度员的工作量，还能提高行车计划的生成质量。 【EN】The invention discloses a method and a device for automatically handling a bus dispatching event. The dispatching method has the advantages that the dispatching plan is automatically generated and the dispatching is automatically completed according to the current resource and service requirements, the problem that the dispatching cannot be carried out according to the originally compiled plan due to the fact that vehicles, drivers and the external environment exist in the dispatching process can be solved, the workload of the dispatchers is reduced, and the generation quality of the driving plan can be improved.

摘要：【中文】本发明提供一种基于FPGA的PD雷达发射波形配置方法及装置，所述装置包括：参数解析模块，用于接收波形配置参数，将其解析为所需要的格式；时序控制模块，用于确定天线发射机的发射时序；DDS回波生成模块，用于生成LFM信号；匹配系数生成模块，用于得到当前配置参数下的匹配滤波系数；回波脉压处理模块，用于自动将AD采集的回波点数补齐为基2点数并进行脉冲压缩处理；数据传输模块，用于将脉冲压缩结果通过调整接口传输到DSP。根据本发明的方案，能够根据不同场景环境和用户需求，半自动化地完成最优的回波目标检测，任意配置适应的回波波形，满足不同探测威力与探测精度。 【EN】The invention provides a PD radar emission waveform configuration method and a device based on FPGA, wherein the device comprises the following steps: the parameter analysis module is used for receiving the waveform configuration parameters and analyzing the waveform configuration parameters into a required format; the time sequence control module is used for determining the transmitting time sequence of the antenna transmitter; the DDS echo generating module is used for generating an LFM signal; the matching coefficient generating module is used for obtaining a matching filter coefficient under the current configuration parameters; the echo pulse pressure processing module is used for automatically supplementing the number of the echo points acquired by the AD into a base 2 point number and performing pulse compression processing; and the data transmission module is used for transmitting the pulse compression result to the DSP through the adjustment interface. According to the scheme of the invention, the optimal echo target detection can be semi-automatically completed according to different scene environments and user requirements, the adaptive echo waveform can be configured at will, and different detection power and detection precision can be met.